The rise of Nvidia is a story planned 30 years ago by its founder and CEO, who saw AI’s primacy coming ten years ago. CC-licensed photo by Diego Torres Silvestre on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 9 links for you. Faster, processor, grill grill! I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Ex-Apple employees new startup wants to bring AI to the desktop • The Verge

Alex Heath:

»

AI chatbots like ChatGPT have, to date, been fairly impersonal, existing outside of the apps and data that we use every day. A new startup by three ex-Apple employees called Software Applications Incorporated hopes to change that.

The company’s CEO, Ari Weinstein, is a repeat founder, having sold his last startup, the iOS automation app Workflow, to Apple in 2017 alongside co-founder and CTO Conrad Kramer. This time, the two have been joined by Kim Beverett, a 10-year Apple vet who was onstage at this year’s WWDC and previously oversaw product management for various teams, including Safari, Messages, FaceTime, and user privacy. 

In their first interview since leaving Apple to start something new, the trio tells me that their focus is on bringing generative AI to the desktop in a way that “pushes operating systems forward.” While they don’t have a product to show off yet, they are prototyping with a variety of large language models, including OpenAI’s GPT and Meta’s Llama 2. The ultimate goal, according to Weinstein, is to recreate “the magic that you felt when you used computers in the ’80s and ’90s.”

“If you turned on an Apple II or an Atari, you’d get this basic console where you could type in basic code as a user and program the computer to do whatever you wanted,” he explains. “Nowadays, it’s sort of the exact opposite. Everybody spends time in very optimized operating systems with pieces of software that are designed to be extremely easy to use but are not flexible.”

An example he gives: “Sometimes you’ve got a browser window open with a schedule on it, and you just want to say, ‘add this to my calendar,’ and somehow, there’s no way to do that… We think that language models and AI give us the ingredients to make a new kind of software that can unlock this fundamental power of computing and make everyday people able to use computers to actually solve their problems.”

«

Workflow makes a good pedigree. Notable how everyone’s trying to recreate Apple’s Knowledge Navigator now.
unique link to this extract

Talking to chatbots is now a $200k job. So I applied • WSJ

Joanna Stern:

»

My father was a prompt engineer, like his father before him. I come from a long line of people who toiled day and night, chatting with generative-AI chatbots.

OK, not true. Prompt engineering is a totally new job that would have sounded crazy even a year ago. But it can pay six-figure salaries to people who extract the best results from the mysterious artificial-intelligence black boxes that are now part of daily life.

A year ago this week, OpenAI released ChatGPT. Not since the iPhone had I been this wowed by new technology. 

Me: How do I keep squirrels out of my bird house?  

ChatGPT: Install a baffle on the bird house pole, which acts as a physical barrier to prevent squirrels from climbing up. Place the bird house away from trees, fences, or buildings to minimize jumping-off points for squirrels. Additionally, consider using a birdhouse with a small entrance hole that’s too tiny for squirrels to fit through.

You had to see the bots’ ability to spit out humanlike answers to believe it. And even then, maybe you shouldn’t believe it. Natural as they sound, many chatbot answers are unwieldy, unhelpful and, sometimes, untrue. (These squirrel solutions do seem legit.) Sure, AI can do some of our writing, computer coding and research jobs. But we wouldn’t want to bet our businesses on them alone.

Enter the prompt engineer! This person fine-tunes the prompts that go into a generative-AI large-language model—aka LLM—to extract valuable but buried information for an employer or its clients. Think of it as an AI whisperer.

And there’s a salary premium for the best whispering. On LinkedIn and the job-search site Indeed, thousands of listings came up for the search term “prompt engineer,” and among those that stated salary, the annual pay could range from $100,000 to over $200,000. People I spoke with said they were seeing similar pay figures.

“We’ll have to wait to see the long-term effects of gen AI, but it’s clear right now that jobs related to the field are surging,” according to a recent report from Indeed. 

«

unique link to this extract

Car dealers say they can’t sell EVs, tell Biden to slow their rollout • Ars Technica

Jonathan Gitlin:

»

Almost 4,000 dealers from around the United States have sent an open letter to President Joe Biden calling for the government to slow down its plan to increase EV adoption between now and 2032.

Despite our robust economy, the US trails both Europe and China in terms of EV adoption. More and more car buyers are opting to go fully electric each year, although even a record 2023 will fail to see EV uptake reach double-digit percentages.

Mindful of the fact that transportation accounts for the largest segment of US carbon emissions and that our car-centric society encourages driving, the US Department of Energy published a proposed rule in April that would alter the way the government calculates each automaker’s corporate average fuel efficiency. If adopted, the new rule would require OEMs to sell many more EVs to avoid large fines. This is in addition to an earlier goal from the White House that calls for one in two new cars sold in 2030 to be EVs.

And that’s too ambitious, says the collection of car dealers, who say that new EVs are piling up on their forecourts and can’t be sold.

…Over the summer, industry analysts at Cox Auto made plenty of headlines with data showing that new EV inventory was growing.

“EVs are selling three times as slow as [internal combustion engine] cars. And so dealers that were forced to make investments on the electrification space, forced to have floorplan financing against these cars, are suddenly running against 90–93 days of inventory turn vis-a-vis 31–32 days for the internal combustion cars. And that obviously is a real issue for them,” said Jantoon Reigersman, COO at TrueCar.

“And then not only are EVs more expensive, but their own salespeople are untrained. They don’t even know how to answer most of the questions they get. A lot of them have 100–200% turnover of their sales staff in a given year,” Reigersman told me.

«

Build out the charging network and the EVs will sell themselves.
unique link to this extract

Don’t be afraid of the iPhone’s NameDrop feature, experts say • The New York Times

Jesus Jiménez:

»

Police departments from New Jersey to California have been sounding the alarm in recent days about NameDrop, a new feature of the Apple iPhone’s latest operating system that allows users to wirelessly exchange contact information.

Apple declined to comment, but experts say the warnings that “scammers and thieves” could exploit the feature to harvest a user’s personal information appear to be overblown, if not entirely unfounded.

For starters, the devices must be practically touching for NameDrop to work, and both users must agree to share the information.

Mark Bartholomew, a law professor who focuses on cyber law at the University at Buffalo, said that NameDrop had enough stopgaps in place to prevent someone’s information from being stolen.
“To the extent there’s panic here about nonconsensual taking of contact information, I’m not that worried,” he said.

…Users hold one device over the other, within a few centimetres, until NameDrop appears on both screens. They can then choose to exchange contact details, or one may simply receive contact information from the other without reciprocating. An exchange can be canceled by pulling a device away or by locking its screen before the transfer is complete.

NameDrop works similarly to AirDrop, which allows users of Apple laptops, iPhones and iPads to exchange photos as long as they are within Bluetooth and Wi-Fi range. But while some people exploited that feature in its early days to harass unsuspecting strangers with explicit images, it appears to be much harder, if not impossible, to use NameDrop to send unwanted information or harvest personal details without consent.

«

Folks always get worked up about this sort of ostensible privacy infiltration, but ignore the drip-drip-drip of smartphone data leaks.
unique link to this extract

Elon Musk to advertisers who are trying to ‘blackmail’ him: ‘Go f— yourself’ • CNBC

Lora Kolodny:

»

Speaking at the 2023 DealBook Summit in New York on Wednesday, Elon Musk, the owner of social media site X (formerly Twitter), scoffed at advertisers boycotting the platform because of antisemitic posts he amplified there.

“If somebody’s gonna try to blackmail me with advertising? Blackmail me with money? Go f—yourself.” He added, “Don’t advertise.”

He also implied that fans of his, and of X, would boycott those advertisers in kind. He specifically took aim at Disney. “The whole world will know that those advertisers killed the company and we will document it in great detail,” Musk threatened. He also told interviewer Andrew Ross Sorkin, “I have no problem being hated. Hate away.”

In recent weeks, Musk has promoted and sometimes verbally endorsed what the White House called “antisemitic and racist hate” on X, formerly Twitter, the social media platform he owns and runs as CTO.

He called those tweets, “one of the most foolish if not the most foolish thing I’ve ever done on the platform.”

“I’m sorry for that tweet or post,” he said. He added, “I tried my best to clarify, six ways to Sunday, but you know at least I think over time it will be obvious that in fact, far from being antisemitic, I am in fact philosemitic.”

«

I can’t decide if Musk’s behaviour is exhausting, like a toddler, or boring, like someone else’s toddler. But you can certainly think that he’s not going to take that much notice of threats around money.
unique link to this extract

Google agrees to pay C$100m a year for news in Canada • FT

Richard Waters:

»

Google has agreed to pay C$100m a year into a fund to support news organisations in Canada as part of a deal with the government, ending a dispute that led it to threaten to cut links to news from its services.

The pact ends a six-month standoff following the passage of an online news law designed to funnel some of the cash that Google and Meta, the parent of Facebook and Instagram, make from online advertising to bolster the finances of news organisations. The dispute blew up into the biggest conflict between the internet giants and a national government over news subsidies since Australia became the first country to pass a law on the issue in 2021.

Meta suspended links to news stories in Canada earlier this year in protest at the law, and Google threatened to follow suit when the law goes into effect in mid-December unless the government diluted the impact of the legislation.

The search giant dug its heels in against being forced to pay for news links in its services, which it feared would set a precedent that could be applied to other types of online links. Rather than hurting the news companies, the internet giants have always claimed that their links deliver valuable traffic to news sites, with Google claiming its news links are worth C$250m a year to Canadian publishers.

«

Frankly, I’m a little surprised: I thought Google would hold out against this. But perhaps it thinks that connecting people with news is more important than any principle. Meta still is doing, and I’d expect that it will continue to.
unique link to this extract

How Jensen Huang’s Nvidia is powering the AI revolution • The New Yorker

Stephen Witt:

»

[Nvidia founder and CEO Jensen] Huang has a practical mind-set, dislikes speculation, and has never read a science-fiction novel. He reasons from first principles about what microchips can do today, then gambles with great conviction on what they will do tomorrow. “I do everything I can not to go out of business,” he said at breakfast. “I do everything I can not to fail.” Huang believes that the basic architecture of digital computing, little changed since it was introduced by I.B.M. in the early nineteen-sixties, is now being reconceptualized.

“Deep learning is not an algorithm,” he said recently. “Deep learning is a method. It’s a new way of developing software.” The evening before our breakfast, I’d watched a video in which a robot, running this new kind of software, stared at its hands in seeming recognition, then sorted a collection of colored blocks. The video had given me chills; the obsolescence of my species seemed near.

Huang, rolling a pancake around a sausage with his fingers, dismissed my concerns. “I know how it works, so there’s nothing there,” he said. “It’s no different than how microwaves work.” I pressed Huang—an autonomous robot surely presents risks that a microwave oven does not. He responded that he has never worried about the technology, not once. “All it’s doing is processing data,” he said. “There are so many other things to worry about.”

«

Nothing like knowing how it all works to make you confident about what it can and can’t do. Huang came up with his plan for Nvidia 30 years ago, and has been following it ever since. *That* is focus.
unique link to this extract

Google ad chief Jerry Dischler stepping down weeks after antitrust trial testimony • NY Post

Thomas Barrabi:

»

Google’s longtime advertising chief Jerry Dischler will step down from his role – weeks after he drew scrutiny over bombshell admissions about the company’s ad practices at the landmark antitrust trial targeting its search empire.

Dischler, who rose to the title of vice president of advertising products at Google in 2020, will be replaced by Vidhya Srinivasan, an ad executive who joined the company in 2019. Srinivasan previously held roles at Amazon and IBM.

“After more than 15 years on Google’s ads business, Jerry Dischler decided to take on a new challenge,” Google senior vice president Prabhakar Raghavan said in a statement Wednesday. “Our ads business helps millions of businesses thrive and we’re grateful to Jerry for his many accomplishments in this area.”

“With a track record of significant innovations across privacy, measurement, AI, search ads and beyond, Vidhya is the natural successor for this role,” Raghavan said.

Dischler had raised eyebrows in September after admitting under questioning by Justice Department antitrust lawyers that Google had silently raised ad prices within its search results in order to hit revenue goals.

“We tend not to tell advertisers about pricing changes,” Dischler said in the Sept. 18 court appearance.

Dischler also confirmed the accuracy of previous sworn testimony from 2020 in which he told federal investigators that the price changes resulted in hikes from 5% to 10% for advertisers on certain search queries. Raising prices any higher would be a “dangerous thing to do” because it could lead advertisers to turn to rivals like TikTok or Meta, he added.

«

And where or what exactly is this “new challenge” that Jerry is taking up? The timing between his uncomfortable testimony and this seems more than coincidental.
unique link to this extract

Study finds no “smoking gun” for mental health issues due to Internet usage • FT via Ars Technica

Tim Bradshaw:

»

A study of more than two million people’s internet use found no “smoking gun” for widespread harm to mental health from online activities such as browsing social media and gaming, despite widely claimed concerns that mobile apps can cause depression and anxiety.

Researchers at the Oxford Internet Institute, who said their study was the largest of its kind, said they found no evidence to support “popular ideas that certain groups are more at risk” from the technology.

However, Andrew Przybylski, professor at the institute—part of the University of Oxford—said that the data necessary to establish a causal connection was “absent” without more cooperation from tech companies. If apps do harm mental health, only the companies that build them have the user data that could prove it, he said.

“The best data we have available suggests that there is not a global link between these factors,” said Przybylski, who carried out the study with Matti Vuorre, a professor at Tilburg University. Because the “stakes are so high” if online activity really did lead to mental health problems, any regulation aimed at addressing it should be based on much more “conclusive” evidence, he added.

“Global Well-Being and Mental Health in the Internet Age” was published in the journal Clinical Psychological Science on Tuesday. In their paper, Przybylski and Vuorre studied data on psychological wellbeing from 2.4 million people aged 15 to 89 in 168 countries between 2005 and 2022, which they contrasted with industry data about growth in Internet subscriptions over that time, as well as tracking associations between mental health and Internet adoption in 202 countries from 2000-19.

“Our results do not provide evidence supporting the view that the Internet and technologies enabled by it, such as smartphones with Internet access, are actively promoting or harming either wellbeing or mental health globally,” they concluded.

«

So it’s not actually quite a clean bill of health: note Przybylski’s point about not having enough data without more cooperation from the tech companies. Which presumably they’d be loth to provide, just in case.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Bike theft, and its lack of solution or prevention, frustrates owners enormously yet the police seem uninterested when it happens. CC-licensed photo by Chetiya Sahabandu on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 10 links for you. Use them wisely. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Backlash over fake female speakers shuts down developer conference • Ars Technica

Ashley Belanger:

»

After an event organizer, Eduards Sizovs, was accused of making up fake female speakers to attract high-profile speakers to an online developer conference called DevTernity, several of the event’s top-billed speakers promptly withdrew.

“You are charging attendees money and they might be making their purchasing decision based on the list of speakers shown to them on the conference website,” wrote former Google developer advocate Kelsey Hightower in a post on the social media platform X confirming that he can no longer participate. “This is misleading at best.”

On Monday, Sizovs confirmed that the conference, DevTernity—which sold tickets for as much as $870 a pop and anticipated 1,300 attendees—was cancelled.

The controversy arose after Gergely Orosz, the author of a popular tech newsletter called Pragmatic Engineering, first posted the allegations on X on Friday. Orosz alleged that out of three women—Kristine Howard, Julia Krisina, and Anna Boyko—scheduled to speak at DevTernity, Krisina and Boyko were fake profiles created by the event organizers to make the event look diverse in order to “successfully attract some of the most heavy-hitter men speakers in tech.”

“To spell it out why this conference generated fake women speakers,” Orosz alleges, it was “because the organizer wants big names and it probably seemed like an easy way to address their diversity concerns. Incredibly lazy.”

Howard—Amazon Web Services’ head of developer relations and the only woman still scheduled to speak at DevTernity—told Ars that the situation is “baffling,” confirming that she has not heard from Sizovs since he emailed her to verify that the event was cancelled.

Sizovs claimed that Boyko, “a demo persona from our test website version,” was added to DevTernity’s speaker list “by mistake” after two real women cancelled their conference appearances due to “reasons out of our control at the worst possible time.” He said that he “noticed the issue in October” but failed to fix it because “it was not a quick fix” and it was “better to have that demo persona while I am searching for the replacement speakers.”

«

Orosz did fantastic work in pinning all this down. The fallout is entirely to be expected, but noticing the anomalies in the first place is the properly important step. AI fakes strike again.
unique link to this extract

Ikea debuts a trio of affordable smart home sensors • The Verge

Thomas Ricker:

»

Ikea’s push to democratize the smart home continues with the introduction of three new Zigbee sensors that won’t break the bank. There’s Parasoll, the door and window sensor; Vallhorn, the motion sensor; and Badring, the water leakage sensor. They’ll all be priced less than $10 when they go on sale globally in the first half of next year.

Parasoll is a typical window and door sensor that can be discretely mounted to trigger an automation when an open / close event is detected. It can also be paired directly with an Ikea light bulb right out of the box without needing to buy and configure an Ikea Home smart hub. It’s priced at €9.99 in Europe, but exact US pricing is yet to be confirmed for it or any of Ikea’s three new sensors.

The Vallhorn motion sensor can be used both indoors and outdoors (with IP44 splash protection against rain) to activate lights or other automations when movement is detected. It’s powered by three AAA batteries and can be paired to directly control up to 10 Ikea smart bulbs right out of the box. It costs just €7.99 and can sense more of the room than Ikea’s existing $14.99 / €12.99 motion sensor that’s smaller but only useable indoors and needs its coin cell battery replaced more frequently.

The Badring water sensor includes a built-in siren (60dBA at 1m) that can alert you when it senses a leak. It can also trigger a mobile notification in the Ikea Home smart app for homes with an Ikea Dirigera hub ($69.99) installed. Sensors like these can save homeowners a ton of money before a water leak has the opportunity to create real damage. It will cost €9.99.

Of the three, the Parasoll and Badring sensors are not compatible with older Trådfri Home smart gateways from Ikea. All support the newer Dirigera hub, of course, which fully integrates the sensors into Ikea’s burgeoning lineup of smart home products and Home smart app. The hub also allows Ikea’s devices to interoperate with smart home ecosystems from Google, Amazon, and Apple when at home or away.

«

When I was researching my book on hacking, I spoke – naturally – to Mikko Hyppönen, then CTO of F-Secure. He told me that the smart home devices he was most impressed by were those from Ikea. And I am too, because they’re easy to use and they integrate with other platforms. If you can think of anything to do with these sensors, these would be a good buy. (Though the lack of compatibility with the old smart gateway is a bore.)
unique link to this extract

Hydrogen heating, village trials and explosion risk • LinkedIn

Michael Liebreich on the trial in Redcar to replace natural gas with hydrogen:

»

Throughout their promotion of the Hydrogen Village Trial in Redcar, Northern Gas Networks (NGN) has referred to the five years of work undertaken on safety. For instance, on its main Redcar Hydrogen Community information page, it says “The plan to provide communities with 100% hydrogen has only been made possible following exhaustive research over the last five years to ensure it can be supplied as safely and reliably as natural gas is today.”

What NGN has been less open about is the fact that it is not planning to follow the recommendations of those five years of work. The Safety Case that emerged from Hy4Heat Work Package 7 was based on passive, or “inherent” safety, with measures including two free-flow valves (which shut off the gas supply in the event of a large leak), and 10cm by 10cm non-closable vents in each room with a hydrogen appliance or substantial plumbing. The residents of Ellesmere Port, made aware of Cadent’s plan to knock in their walls at a public meeting with experts (of which I was one), gave that idea short shrift.

Verbally, NGN has told residents it is not planning to implement the measures laid out in the Hy4Heat Safety Case, but to switch to an “active” safety strategy based on the use of hydrogen sensors. Its problem is that although it is working with the HSE to develop the sensors, no Safety Case based on hydrogen sensors for space heating has yet been published – let alone approved by the HSE, let alone communicated by NGN as part of the trial, let alone discussed by residents, let alone accepted by them as adequate.

NGN has repeatedly accused me and the other experts who appeared at the public meetings in Ellesmere Port and Redcar of spreading misinformation. They say they would never do anything unsafe – but that is gaslighting: I never said they would, and in any case the HSE would not let them. What I did say, and continue to say, is that NGN are not planning to follow the published Safety Case, approved by the HSE for the hydrogen heating trials.

«

It’s quite difficult to make out, but reading through towards the end, Liebreich compares the new plans for hydrogen to the old “town gas”, which was 50% hydrogen and used up to the 1970s. And back then, there were eight times as many explosions as with modern gas. If you go to 100% hydrogen.. why would things be safer?
unique link to this extract

I have owned 11 bikes. This is how they were stolen • The Times

Tom Whipple:

»

Bike 8 was stolen from a station cycle rack, where I had parked it directly beneath a camera. This time, I thought, we have them. Triumphantly I went to the police. “Look!” I said. “You will be able to see them.” They refused to look at the footage unless I could narrow it down to a window shorter than a few hours. This is, I discovered, a common response.

Afterwards I found a chatroom thread among Cambridge computer scientists, one of whom had also been told that unless he could pin down the moment of theft no one would look at the footage. He said he had tried to explain sorting algorithms to police — he was a computer scientist, after all.

You don’t watch the whole thing, he said. You use a binary search. You fast forward to halfway, see if the bike is there and, if it is, zoom to three quarters of the way through. But if it wasn’t there at the halfway mark, you rewind to a quarter of the way through. It’s very quick. In fact, he had pointed out, if the CCTV footage stretched back to the dawn of humanity it would probably have only taken an hour to find the moment of theft. This argument didn’t go down well.

I made a (slightly more diplomatic) nuisance of myself and they eventually looked at the footage. The policewoman I dealt with was lovely about it, but in the end the image wasn’t clear. Maybe they were right not to bother.

«

Bicycle theft – along with phone theft – is endemic and enormously annoying to victims, who feel that the police don’t care if nobody is hurt (and won’t do anything that might involve the faintest possibility of harm, such as confronting a potential criminal if, say, a phone is transmitting its location). The police, of course, aren’t going to stand up and say that they don’t care about property crime, but it’s quite close to it.
unique link to this extract

An idea-to-video platform that brings your creativity to motion • Pika

»

Video is at the heart of entertainment, yet the process of making high-quality videos to date is still complicated and resource-intensive. When we started Pika six months ago, we wanted to push the boundaries of technology and design a future interface of video making that is effortless and accessible to everyone. Since then, we’re proud to have grown the Pika community to half a million users, who are generating millions of videos per week.
 
Our vision for Pika is to enable everyone to be the director of their own stories and to bring out the creator in each of us. Today, we reached a milestone that brings us closer to our vision. We are thrilled to unveil Pika 1.0, a major product upgrade that includes a new AI model capable of generating and editing videos in diverse styles such as 3D animation, anime, cartoon and cinematic, and a new web experience that makes it easier to use. You can join the waitlist for Pika 1.0 at https://pika.art.
 
We are also excited to announce our fundraising milestones: we have raised $55m, initiated with pre-seed and seed rounds

«

Prompt-to-video. There will soon be a ton of companies doing this; yet just as with Pixar, what will mark out the great creators will be their ability to tell stories, not to create animation. What makes Toy Story 1 wonderful is its story, not – viewed now – the quality of its videos.

Also: Stable Diffusion is now offering similar stuff.
unique link to this extract

Is Argentina the first AI election? • The New York Times

Jack Nicas and Lucía Cholakian Herrera, in an article written before the result of the election:

»

The posters dotting the streets of Buenos Aires had a certain Soviet flair to them.

There was one of Argentina’s presidential candidates, Sergio Massa, dressed in a shirt with what appeared to be military medals, pointing to a blue sky. He was surrounded by hundreds of older people — in drab clothing, with serious, and often disfigured, faces — looked toward him in hope.

The style was no mistake. The illustrator had been given clear instructions.

“Sovietic Political propaganda poster illustration by Gustav Klutsis featuring a leader, masssa, standing firmly,” said a prompt that Mr. Massa’s campaign fed into an artificial-intelligence program to produce the image. “Symbols of unity and power fill the environment,” the prompt continued. “The image exudes authority and determination.”

Javier Milei, the other candidate in Sunday’s runoff election, has struck back by sharing what appear to be AI images depicting Mr. Massa as a Chinese communist leader and himself as a cuddly cartoon lion. They have been viewed more than 30 million times.

Argentina’s election has quickly become a testing ground for AI in campaigns, with the two candidates and their supporters employing the technology to doctor existing images and videos and create others from scratch. AI has made candidates say things they did not, and put them in famous movies and memes. It has created campaign posters, and triggered debates over whether real videos are actually real.

AI’s prominent role in Argentina’s campaign and the political debate it has set off underscore the technology’s growing prevalence and show that, with its expanding power and falling cost, it is now likely to be a factor in many democratic elections around the globe.

Experts compare the moment to the early days of social media, a technology offering tantalizing new tools for politics — and unforeseen threats.

«

The irony is that the article implies that Milei has no chance because of all the AI content being aimed at him. Whereas we know the result was in fact completely the opposite. Sometimes you need to evaluate these things after the fact.
unique link to this extract

Why Apple is working hard to break into its own phones • The Independent

Andrew Griffin:

»

Unlike with software, where even significant security holes can be fixed relatively simply with a security update, hardware is out of Apple’s hands once a customer buys it. That means that it must be tested years in advance with every possible weakness probed and fixed up before the chip even makes it anywhere near production.

Apple’s chips have to be relied upon to encrypt secure data so that it cannot be read by anyone else, for instance; pictures need to be scrambled before they are sent up to be backed up on iCloud, for instance, to ensure that an attacker could not grab them as they are transferred. That requires using detailed and complicated mathematical work to make the pictures meaningless without the encryption key that will unlock them.

There are various ways that process might be broken, however. The actual chip doing the encryption can show signs of what it is doing: while processors might seem like abstract electronics, they throw out all sorts of heats and signals that could be useful to an attacker. If you asked someone to keep a secret number in their head and let you try and guess it, for instance, you might tell them to multiply the number by two and see how long it takes and how hard they are thinking; if it’s a long time, it suggests the number might be especially big. the same principle is true of a chip, it’s just that the signs are a little different.

And so Apple gets those chips and probes them, blasts them with precisely targeted lasers, heats them up and cools them down, and much more besides. The engineers in its Paris facilities doing this work are perhaps the most highly capable and well resourced hackers of Apple’s products in the world; they just happen to be doing it to stop everyone else doing the same. If they find something, that information will be distributed to colleagues who will then work to patch it up. Then the cycle starts all over again.

«

It’s not hugely detailed, but it does indicate that protecting against hacking is something they’re very serious about.
unique link to this extract

China’s Transsion, world’s fifth largest smartphone maker, keeps ascending • Nikkei Asia

Takashi Kawakami:

»

China’s Transsion Holdings, one of the world’s top five smartphone makers, continues to grow globally, with its market share approaching that of major Chinese manufacturer Oppo, on the back of a strong showing in Africa and South Asia.

Transsion’s shipments rose 35%, year-on-year, to 26 million units in the three months ended September, with its global market share reaching 8.6%, maintaining the No. 5 position it earned in the April to June period and narrowing the gap with Oppo, at 8.9%, according to U.S. research specialist IDC.

Transsion is benefiting from a sharp recovery in smartphone demand after declines in sales and profit for the year through December 2022, due in part to the COVID-19 pandemic. In the nine months through September this year, its sales rose 20%, year-on-year, to 43 billion yuan ($5.8 billion) and its net profit jumped 70% to 3.8 billion yuan.

At a Belt and Road Initiative event in Beijing last month, Transsion’s President and Chairman Zhu Zhaojiang, said the company will “uncover the driving force behind Africa’s economic growth.”

«

The biggest smartphone company you’ve never heard of (or whose products maybe you’ve never seen). Though it’s not just content in the low-end space: it’s going to launch a foldable later this year.
unique link to this extract

The renewable energy disaster far more deadly than Chernobyl • RealClearScience

Ross Pomeroy:

»

Decades ago, a single energy disaster left three million acres of land uninhabitable to humans and killed between 85,600 and 240,000 people. A casual student of history might assume these shocking statistics refer to the Chernobyl nuclear accident, but that would be incorrect. No, this catastrophic specter was the fault of the Banqiao Dam collapse in Henan, China. By comparison, Chernobyl killed fifteen times fewer people and desolated an area of land one-sixth as large.

Though sharply different in magnitude, the Banqiao and Chernobyl disasters occurred under similar circumstances. Constructed by the Chinese Communist party during the Great Leap Forward, with guidance from the Soviet Union, the dam was poorly designed and hastily constructed – just like the Chernobyl nuclear power plant. Moreover, party officials wanted it to retain as much water as possible because it would be “more revolutionary.” Hydrologist Chen Xing, Chief Engineer of dam projects, warned against that superficial goal and advocated for additional safety features. He was overruled and later reassigned.

Chen Xing’s warnings proved prescient in early August 1975 when Typhoon Nina battered Banqiao and dumped a meter of water in three days. The dam didn’t stand a chance. As it began to disintegrate under heavy strain, one of the workers struggling to save the dam reportedly shouted “Chu Jiaozi!” The river dragon has come…

Six hundred million cubic meters of water would eventually pour through the remains of the ruptured dam, forming a wall of water six meters high and twelve kilometers wide moving up to fifty kilometers per hour.

«

An inland, human-made tsunami. The 1970s feel like a time of hubris: errors in nuclear engineering, in dam building, and so on.
unique link to this extract

Brazil’s mysterious tunnels made by giant sloths • BBC Travel

Sarah Brown:

»

In 2009, a farmer was driving through his corn field in the south of Brazil when he suddenly felt his tractor sink and lurch to one side, making the vehicle shudder to a halt. He jumped out and saw the wheel had sunk deep into the dry soil.

Much to the farmer’s shock, the tractor had broken through what looked like top of an underground cavity. Hearing about this unusual find, researchers came to investigate and were surprised to find a tunnel nearly 2m high by almost 2m wide and about 15m long running across the field and right under the farmer’s house. Deep claw marks embedded into the walls indicated its past occupant was not human.

The farmer had stumbled upon a puzzling subject in palaeontology that is still unfolding today. He’d uncovered a megafauna paleoburrow, a prehistoric tunnel dug through rock by what Luiz Carlos Weinschutz, a geologist and one of the scientists who visited the farmer’s property, concluded was the work of a giant ground sloth or giant armadillo from at least 10,000 years ago.

These giant ground sloths, described in one paper as “a hamster the size of an elephant”, were far removed from today’s unhurried, tree-dwelling ones. They grew up to 4m long and walked on all fours, although research suggests some could stand and move bipedally. Almost 100 different species of sloths roamed the Americas between 15 million to 10,000 years ago alongside car-sized giant armadillos that also dug long tunnels through rocks in Brazil.

«

I think you need to see the picture of the Very Large Sloths. It’s there at the article if you click the link.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

The smartphone headphone jack has become an endangered species since Apple killed its own with the iPhone 7: CC-licensed photo by Ivan Radic on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 10 links for you. Plug and play. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

After 151 years, Popular Science will no longer offer a magazine • The Verge

Emma Roth:

»

PopSci, which covers a whole range of stories related to the fields of science, technology, and nature, published its first issue in 1872. Things have changed a lot over the years, with the magazine switching to a quarterly publication schedule in 2018 and doing away with the physical copies altogether after 2020.

In a post on LinkedIn, former PopSci editor Purbita Saha commented on the magazine’s discontinuation, stating she’s “frustrated, incensed, and appalled that the owners shut down a pioneering publication that’s adapted to 151 years worth of changes in the space of a five-minute Zoom call.” Layoffs have impacted journalists on the science beat particularly hard in recent weeks. National Geographic cut the remainder of the magazine’s editorial staff in June, followed by Gizmodo laying off its last climate reporter, and CNBC shuttering its climate desk last week.

“PopSci is a phenomenal brand, and as consumer trends shift it’s important we prioritize investment in new formats,” [PopSci owner Recurrent Ventures flack Cathy] Herbert tells The Verge. “We believe that the content strategy has to evolve beyond the digital magazine product. A combination of its news team, along with commerce, video, and other initiatives, will produce content that naturally aligns with PopSci’s mission.”

PopSci laid off several employees earlier this month, leaving around five editorial staff members
In addition to dropping its magazine format, PopSci laid off several employees earlier this month, leaving around five editorial staff members and “a few” workers on the publication’s commerce team, according to Axios. The digital media group Recurrent Ventures acquired PopSci in 2021 and named its third CEO in three years just one week before the layoffs hit.

«

Paper-based magazines are dropping like leaves in autumn. Though the job cuts in digital media doesn’t make for easy reading either.
unique link to this extract

Meta designed platforms to get children addicted, court documents allege • The Guardian

Kari Paul and agencies:

»

Instagram and Facebook parent company Meta purposefully engineered its platforms to addict children and knowingly allowed underage users to hold accounts, according to a newly unsealed legal complaint.

The complaint is a key part of a lawsuit filed against Meta by the attorneys general of 33 states in late October and was originally redacted. It alleges the social media company knew – but never disclosed – it had received millions of complaints about underage users on Instagram but only disabled a fraction of those accounts. The large number of underage users was an “open secret” at the company, the suit alleges, citing internal company documents.

In one example, the lawsuit cites an internal email thread in which employees discuss why a 12-year-old girl’s four accounts were not deleted following complaints from the girl’s mother stating her daughter was 12 years old and requesting the accounts to be taken down. The employees concluded that “the accounts were ignored” in part because representatives of Meta “couldn’t tell for sure the user was underage”.

The complaint said that in 2021, Meta received over 402,000 reports of under-13 users on Instagram but that 164,000 – far fewer than half of the reported accounts – were “disabled for potentially being under the age of 13” that year. The complaint noted that at times Meta has a backlog of up to 2.5m accounts of younger children awaiting action.

The complaint alleges this and other incidents violate the Children’s Online Privacy and Protection Act, which requires that social media companies provide notice and get parental consent before collecting data from children.

«

unique link to this extract

Sports Illustrated published articles by fake, ai-generated writers • Futurism

Maggie Harrison:

»

There was nothing in Drew Ortiz’s author biography at Sports Illustrated to suggest that he was anything other than human. “Drew has spent much of his life outdoors, and is excited to guide you through his never-ending list of the best products to keep you from falling to the perils of nature,” it read. “Nowadays, there is rarely a weekend that goes by where Drew isn’t out camping, hiking, or just back on his parents’ farm.”

The only problem? Outside of Sports Illustrated, Drew Ortiz doesn’t seem to exist. He has no social media presence and no publishing history. And even more strangely, his profile photo on Sports Illustrated is for sale on a website that sells AI-generated headshots, where he’s described as “neutral white young-adult male with short brown hair and blue eyes.”

Ortiz isn’t the only AI-generated author published by Sports Illustrated, according to a person involved with the creation of the content who asked to be kept anonymous to protect them from professional repercussions. “There’s a lot,” they told us of the fake authors. “I was like, what are they? This is ridiculous. This person does not exist.”

“At the bottom [of the page] there would be a photo of a person and some fake description of them like, ‘oh, John lives in Houston, Texas. He loves yard games and hanging out with his dog, Sam.’ Stuff like that,” they continued. “It’s just crazy.”

The AI authors’ writing often sounds like it was written by an alien; one Ortiz article, for instance, warns that volleyball “can be a little tricky to get into, especially without an actual ball to practice with.”

According to a second person involved in the creation of the Sports Illustrated content who also asked to be kept anonymous, that’s because it’s not just the authors’ headshots that are AI-generated. At least some of the articles themselves, they said, were churned out using AI as well. “The content is absolutely AI-generated,” the second source said, “no matter how much they say that it’s not.”

After we reached out with questions to the magazine’s publisher, The Arena Group, all the AI-generated authors disappeared from Sports Illustrated’s site without explanation. Our questions received no response.

«

Such a sad fall for a once-iconic magazine that was home to some of the greatest sports writers.
unique link to this extract

Auto emissions could have dropped by 30%, if it weren’t for SUVs: report • Electrek

Jennifer Mossalgue:

»

A new report gives us a glimpse of what our world could look like if there weren’t so many big, hulking SUVs cruising around. Because of the rise in electric vehicles, carbon emissions from automobiles could have dropped by more than 30% over the past 10 years, except they haven’t – and that’s because of our global appetite for jumbo cars, the report authors say.

From 2010 to 2022, if vehicles had stayed the same size and the bloated SUV trend had never happened, carbon emissions could have been reduced by more than 30%, according to a report from the Global Fuel Economy Initiative (GFEI). Instead, automotive emissions only dropped 4.2%, essentially undoing all the good benefits of electric vehicles.

SUVs represent 51% of the new car market, and the average light-duty vehicle weight has bulked up to an all-time high of more than 1.5 tonnes. The size of SUVs is growing, with a footprint averaging around 4.2 square meters (about 45 square feet). Plus, automakers make a huge profit from SUVs, which are sold at premium prices but have a proportionally lower manufacturing cost, so they are eager to market them to consumers.

Electric vehicles, which represent 15% of global new car sales in 2022, use three to six times less energy than ICE vehicles to travel the same distance. Markets with strong growth in the EV sector, including China and Europe, saw the largest annual energy efficiency improvements of close to 6%. North America, which has a lower market uptake of EVs, recorded a yearly improvement rate of 1.6%.

«

Groan. Can America ever do the right thing?
unique link to this extract

Is it time to concede Apple was right to eliminate the headphone jack? • Perfect Rec

Wally Nowinski on the iPhone 7 decision, seven years ago:

»

A 3.5mm headphone jack isn’t enormous, but every cubic millimeter of space counts. In 2017, Razer’s CEO, Min-Liang Tan, claimed that dropping the headphone jack allowed Razer to increase battery capacity by about 500 mAh, or 12.5%.

This seems like it is probably an upper bound estimate and it’s possible that the compact form factor of Razer phones was more impacted by layout restrictions imposed by a headphone jack than a more traditional phone design.

We can also estimate the approximate space saved for additional battery capacity. A 3.5mm headphone jack is about 200 cubic millimeters including the port and external components. The battery pack on the base model iPhone 15 is about 20,300 cubic millimeters. By that measure, not having a headphone jack enables Apple to make the battery pack about 1% larger. It’s also worth noting that the iPhone 15 is about 24% larger than the iPhone 7, so the initial space saving was even more significant back in 2016.

200 cubic millimeters might not sound like a lot, but space inside a phone is so valuable that manufacturers are constantly looking for more ways to save it. The recent move by phone manufacturers from the traditional SIM card reader to the eSIM was also a space saving move. But even the eSIM takes up about 20 cubic millimeters. The upcoming iSIM will be integrated as part of the SoC instead of its own small chip, taking up almost no space. This underlines that manufacturers are willing to make fairly tough changes in order to get 1/10 the space savings as removing the headphone jack.

«

And, as he also points out, other manufacturers – Google, Samsung, Razer – followed suit. The phone headphone jack is an endangered species.
unique link to this extract

Israel tells Elon Musk Starlink can only operate in Gaza with its approval • FT

Chloe Cornish:

»

The world’s richest man declared late last month that his satellite internet service Starlink would “support connectivity to internationally recognised aid organisations in Gaza”, which has suffered lengthy blackouts under Israel’s bombardment.

But on Monday, Israeli communications minister Shlomo Karhi posted on X that the entrepreneur had “reach[ed] a principle understanding” with the ministry. “Starlink satellite units can only be operated in Israel with the approval of the Israeli Ministry of Communications, including the Gaza Strip,” Karhi said.

Musk has not yet publicly confirmed any deal.

The SpaceX and Tesla chief executive is visiting the Jewish state for the first time since Hamas’s October 7 assault on southern Israel, which killed 1,200 people and triggered a war between Israel and the militant group.

Israel’s ferocious retaliatory bombardment and siege of the strip has created a humanitarian crisis, killed more than 13,300 people and led to prolonged blackouts. These have obstructed rescue efforts, notably by preventing ambulances from locating wounded people.

Musk’s visit to Israel coincides with the last day of a four-day pause in hostilities, and comes as advertisers pile pressure on X over a rise in antisemitism on the platform.

«

You’re thinking: how could Israel control a satellite-based phone system?

»

The Starlink signal is received through small satellite dishes called terminals. But Musk said in October that no terminals had actually attempted to connect from besieged Gaza, and Israel controls the movement of goods into the coastal enclave.

«

Perhaps there would also be pressure on Tesla, perhaps. And Starlink itself if it wanted to sell in Israel. Plus perhaps Starlink can refuse connections from specific geographic locations.
unique link to this extract

This high-tech shirt helps deaf and hard-of-hearing patrons feel music • Smithsonian Magazine

Julia Binswanger:

»

Chicago’s Lyric Opera is aiming to make its performances more accessible via the SoundShirt, a garment that vibrates to match the music.

In October, the Lyric became the first opera company to offer the shirts to audience members who are deaf or hard of hearing. The device comes from a London-based wearable tech brand called CuteCircuit. Each shirt costs about $1,900, but interested guests can reserve one for special performances at $20 a ticket, according to Axios’ Carrie Shepherd.

“I am proud that Lyric Opera of Chicago will be the first opera company in the world to bring this new technology to its live audiences,” says Anthony Freud, the Lyric’s general director, in a statement. “The SoundShirt reinforces Lyric’s commitment to accessibility and to broadening the impact of our live performances on all audience members.”

The SoundShirt is worn like a lightweight jacket and features 16 small motors throughout. Microphones are placed around the orchestra on stage to record specific instruments and send a live signal to activate vibrations in the shoulders, forearms and upper and lower back.

Rachel Arfa, commissioner of Chicago’s Mayor’s Office for People with Disabilities, recently tested the SoundShirt at a production of West Side Story. “When Lyric approached me with this shirt, I was highly skeptical,” she tells the Washington Post’s Michael Andor Brodeur. “There are often technical solutions designed by people without disabilities for people with disabilities that do not solve barriers that we have.”

The technology certainly isn’t for everyone. The Chicago Sun-Times’ Stefano Esposito says wearing a SoundShirt feels like “your torso has become home to an entire hive of non-stinging bees.”

“It’s not an unpleasant sensation,” he writes, “just odd, very odd.”

«

Clever. (Though I think the correct phrase to cover all those people who could benefit from displacing the sound is “hearing-impaired”.)
unique link to this extract

Global pay TV penetration to fall for the first time in 2024 • Ampere Analysis

Rory Gooderick:

»

Global pay TV penetration (the number of pay TV subscriptions relative to the number of households) is set to decline for the first time ever in 2024 following a peak penetration of 60.3% in Q4 2023. This decline will continue into the forecast period, with a drop of almost 4 percentage points by the end of 2028, according to Ampere’s latest forecasts, which cover 96 markets.

This decline in pay TV penetration has been driven primarily by the Americas, and in particular North America which has seen its pay TV penetration almost halve from a high of 84% in 2009 to 45% in 2023. In the case of North America, this drop has been caused by a combination of high costs (currently over $90 per month) and competition from a mature SVoD market which is driving customers increasingly to cut the cord.

However, the recent distribution deal between Disney and Charter in the US, which saw select Disney streaming products bundled into Charter’s TV packages, demonstrates that cable operators in the region remain a powerful force as distribution partners, giving streamers the ability to reach a larger and potentially untapped audience base. In addition to North America, Latin America has also shown large declines in pay TV penetration, with a drop of around 10 percentage points since its peak of 42% in 2016.

On the contrary, the APAC and Europe have shown the highest penetration growth in recent years, with large gains coming from China, especially after China Mobile acquired an IPTV license in 2018.

«

So easy to forget China, the iceberg of content consumption and production.
unique link to this extract

X has become a ‘global sewer,’ mayor of Paris says • NY Times

Liz Alderman:

»

In a lengthy post, Ms. [Anne] Hidalgo said that X had veered from its original incarnation as a platform for making information freely available into one whose algorithms exacerbated attacks on people seeking peaceful political debate. “Facts are irrelevant,” she said. She further cited a report released by X that ranked France the No. 1 country in Europe for postings of “violent and illegal content.”

​​A spokesman for X did not reply to a request for comment. A query sent to Twitter’s press office generated an automated response: “Busy now, please check back later.”

Ms. Hidalgo, a Socialist mayor who has made the environment the hallmark of her nearly 10 years in office, has herself faced a torrent of negative comments on X for policies that have included closing major streets to car traffic in order to make way for bikes and plans to limit speeds on the freeways circling Paris. She said that proponents of fossil fuels had flooded X with misinformation about the need for an ecological transformation.

Ms. Hidalgo faced a stream of scrutiny on X this month after a visit to Tahiti, a French territory, where the surfing competition will take place in the 2024 Olympic Games hosted by France. After extending her stay there to include a vacation, which she paid for, a slew of criticism flooded her X feed, including calls for her to step down.

“We need more than ever to keep real democracy alive,” she wrote in her announcement Monday. “Twitter hinders debate, the quest for truth, and the serene and constructive dialogue needed between human beings. I refuse to endorse this evil scheme.”

«

As if to prove it, many of the replies to her tweet came from angry paid-for-verification users, and weren’t complimentary.
unique link to this extract

Net zero risks wiping $3 trillion from oil and gas companies worth • Daily Telegraph

Jonathan Leake:

»

The oil and gas industry faces losses of more than $3 trillion (£2.4 trillion) because of net zero, the International Energy Agency (IEA) has warned.

The IEA said companies will become increasingly risky investments, potentially losing half their overall valuation, as the world moves to restrict greenhouse gas emissions.

It has accused the global oil and gas industry of failing to understand or respond to the deepening global climate crisis and warned that the result could be a catastrophic loss of value for investors unless companies change course.

Pension and investment funds that rely on oil and gas companies for large chunks of their investment returns could face disastrous declines over the next two decades as a result, the IEA warned.

The Paris-based organisation said the value of the private oil and gas industry, which stands at $6 trillion, will fall by a quarter if all current climate goals set by governments around the world are met.

If targets are toughened up to put the world on course to limit global warming to 1.5ºC, as leaders committed to do under the Paris Climate Agreement in 2015, then as much as 60% of the industry’s worth could be wiped out, the IEA said. This would mean companies collectively lose more than $3 trillion of value.

«

Note the faint undertone in this story, which appeared in the Daily Telegraph, favourite of the Tory-voting stock-owning (ancient) generation: “net zero” will do these things to companies’ valuations, and therefore net zero is bad. Rather than these companies are contributing to wrecking the planet, and are therefore bad and deserve to fall in value concomitant to the damage they’re causing.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Ten-pin bowling enthusiasts are upset at the use of “strings” to retain pins rather than more complex mechanical systems because they change how the pins interact. But they’re cheaper. CC-licensed photo by Ginny on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

A selection of 10 links for you. Use them wisely. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

ChatGPT generates fake data set to support scientific hypothesis • Nature

Miryam Naddaf:

»

Researchers have used the technology behind the artificial intelligence (AI) chatbot ChatGPT to create a fake clinical-trial data set to support an unverified scientific claim.

In a paper published in JAMA Ophthalmology on 9 November1, the authors used GPT-4 — the latest version of the large language model on which ChatGPT runs — paired with Advanced Data Analysis (ADA), a model that incorporates the programming language Python and can perform statistical analysis and create data visualizations. The AI-generated data compared the outcomes of two surgical procedures and indicated — wrongly — that one treatment is better than the other.

“Our aim was to highlight that, in a few minutes, you can create a data set that is not supported by real original data, and it is also opposite or in the other direction compared to the evidence that are available,” says study co-author Giuseppe Giannaccare, an eye surgeon at the University of Cagliari in Italy.

The ability of AI to fabricate convincing data adds to concern among researchers and journal editors about research integrity. “It was one thing that generative AI could be used to generate texts that would not be detectable using plagiarism software, but the capacity to create fake but realistic data sets is a next level of worry,” says Elisabeth Bik, a microbiologist and independent research-integrity consultant in San Francisco, California. “It will make it very easy for any researcher or group of researchers to create fake measurements on non-existent patients, fake answers to questionnaires or to generate a large data set on animal experiments.”

«

Yikes. Related: “scientific sleuths spot dishonest ChatGPT use in papers“. (Paywalled.) (Thanks Gregory B for the link.)
unique link to this extract

There is a scientific fraud epidemic — and we are ignoring the cure • FT

Anjuna Ahuja:

»

As the Oxford university psychologist Dorothy Bishop has written, we only know about the ones [committing scientific fraud] who get caught. In her view, our “relaxed attitude” to the scientific fraud epidemic is a “disaster-in-waiting”. The microbiologist Elisabeth Bik, a data sleuth who specialises in spotting suspect images, might argue the disaster is already here: her Patreon-funded work has resulted in over a thousand retractions and almost as many corrections.

That work has been mostly done in Bik’s spare time, amid hostility and threats of lawsuits. Instead of this ad hoc vigilantism, Bishop argues, there should be a proper police force, with an army of scientists specifically trained, perhaps through a masters degree, to protect research integrity.

It is a fine idea, if publishers and institutions can be persuaded to employ them (Spandidos, a biomedical publisher, has an in-house anti-fraud team). It could help to scupper the rise of the “paper mill”, an estimated $1bn industry in which unscrupulous researchers can buy authorship on fake papers destined for peer-reviewed journals. China plays an outsize role in this nefarious practice, set up to feed a globally competitive “publish or perish” culture that rates academics according to how often they are published and cited.

Peer reviewers, mostly unpaid, don’t always spot the scam. And as the sheer volume of science piles up — an estimated 3.7m papers from China alone in 2021 — the chances of being rumbled dwindle. Some researchers have been caught on social media asking to opportunistically add their names to existing papers, presumably in return for cash.

«

Plus AI content generators helping the churn. But the real drivers of this are two factors: 1) academic institutions requiring publication for reputation 2) science publishers which are motivated by generating the most content, not the best, and which have a natural bias against publishing corrections or negations.
unique link to this extract

Bowling, that simple game of our youth, is being turned upside-down by technology • LA Times

David Wharton:

»

Bowling alleys across the country are ditching traditional pinsetters — the machines that sweep away and reset pins — in favour of contraptions that employ string. Think of the pins as marionettes with nylon cords attached to their heads. Those that fall are lifted out of the way, as if by levitation, then lowered back into place after each frame.

String pinsetters mean big savings, maybe salvation, for an industry losing customers to video games and other newfangled entertainment. That is why the US Bowling Congress recently certified them for tournaments and league play.

But there is delicate science at play here. Radius of gyration, coefficient of restitution and other obscure forces cause tethered pins to fly around differently than their free-fall counterparts. They don’t even make the same noise.

Faced with growing pushback, the bowling congress published new research this month claiming the disparity isn’t nearly as great as people think. [Keen bowler Kevin] Mills seems dubious on a recent night when he visits a San Fernando Valley bowling alley that has made the switch. “The physics are entirely different,” he says. “It’s a big deal in our world.”

…In the 1960s, the U.S. had about 11,500 bowling alleys, or “houses,” according to industry reports. Such establishments were referred to as “the poor man’s country club.”

Though the sport has remained popular, with about 67 million Americans playing at least once a year, current demand supports only 3,000 or so houses.

“Some of the decline has to do with cost to operate and square footage,” says Chad Murphy, the bowling congress’ executive director. “If [houses] can lower their costs, that’s a good thing.”

«

But the pins don’t fall in the same way, of course. Problem is that the old mechanical systems were prone to failure, and upkeep was costly in parts and time. Technology making a sport.. worse?
unique link to this extract

X may lose up to $75m in revenue as more advertisers pull out • The New York Times

Ryan Mac and Kate Conger:

»

Internal documents viewed by The New York Times this week show that the company is in a more difficult position than previously known and that concerns about Mr. Musk and the platform have spread far beyond companies including IBM, Apple and Disney, which paused their advertising campaigns on X last week. The documents list more than 200 ad units of companies from the likes of Airbnb, Amazon, Coca-Cola and Microsoft, many of which have halted or are considering pausing their ads on the social network.

The documents come from X’s sales team and are meant to track the impact of all the advertising lapses this month, including those by companies that have already paused and others that may be at risk of doing so. They list how much ad revenue X employees fear the company could lose through the end of the year if advertisers do not return.

On Friday, X said in a statement that $11m in revenue was at risk and that the exact figure fluctuated as some advertisers returned to the platform and others increased spending. The company said the numbers viewed by The Times were either outdated or represented an internal exercise to evaluate total risk.

The advertising freezes come during the final three months of the year, which is traditionally the social media company’s strongest quarter as brands run holiday promotions for events such as Black Friday and Cyber Monday. In the last three months of 2021 — the last year the company reported fourth-quarter earnings before Mr. Musk took over — the company recorded $1.57bn in revenue, of which nearly 90% came from advertising.

«

The next question is what pressure that will put on Twitter/X’s debt repayment schedule. Musk is going to have to fund the company rather more than he expected, with no prospect of relief.
unique link to this extract

Hacking my filter coffee machine • diziet

Ian Jackson:

»

I have a Morphy Richards filter coffee machine. It makes very good coffee. But the display and firmware are quite annoying:

• After it has finished making the coffee, it will keep the coffee warm using its hotplate, but only for 25 minutes. If you want to make a batch and drink it over the course of the morning that’s far too short.

• It has a timer function. But it only has a 12 hour clock! You can’t retire upstairs on a Friday night, having programmed the coffee machine to make you coffee at a suitable post-lie-in time. If you try, you are greeted with apparently-inexplicably-cold coffee.

• The buttons and UI are very confusing. For example, if it’s just sitting there keeping the coffee warm, and you pour the last, you want to turn it off. So you press the power button. Then the display lights up as if you’ve just turned it on! (The power LED is in the power button, which your finger is on.) If you know this you can get used to it, but it can confuse guests.

Also, I’m lazy and wanted to be able to cause coffee to exist from upstairs in bed, without having to make a special trip down just to turn the machine on.

«

Necessity of caffeine is the parent of intervention. Remarkable how often coffee features in internet-related inventions.
unique link to this extract

‘You can walk around in a T-shirt’: how Norway brought heat pumps in from the cold • The Guardian

Ajit Niranjan:

»

When Glen Peters bought a heat pump for his home in Oslo he wasn’t thinking about the carbon it would avoid. Convenience played a role; a fireplace was too much of a hassle – the effort of having to buy, prepare and store the wood – and the wall-mounted radiators are too dusty. “They’re a pain in the ass to clean,” said Peters (who is actually a climate scientist).

But the main factor, according to Peters, who had recently swapped to underfloor heating, was money.

In most of Europe, fitting a heat pump is one of the most powerful actions a person can take to reduce their carbon footprint. But in Norway, where clean-yet-inefficient electrical resistance heaters have long been common, upgrading to a heat pump is often a purely financial decision – one to which Peters came late. Two-thirds of households in this Nordic country of 5 million people have a heat pump, more than anywhere else in the world.

For many years, Norwegians and their neighbours heated their homes with fossil fuels. But during the 1973 oil crisis, when prices shot up, the country’s political leaders made a conscious choice to promote alternatives, and, unlike their counterparts elsewhere, they did not back away from that decision once the crisis eased.

Denmark rolled out an extensive district heating system. Norway, Sweden and Finland moved more towards heating with wood or electricity. They began to price carbon in the 1990s, and a mix of grants and taxes tipped the balance further away from oil long after the crisis was over.

«

That phrase “had recently swapped to underfloor heating” is a brisk few words to cover rather a lot of potentially expensive work. Sure, if my house had underfloor heating then I’d think a heat pump could be a great idea. But if I had to dig up every floor.. maybe not.
unique link to this extract

Twitter’s former head of Trust and Safety finally breaks her silence • WIRED

Lauren Goode managed to track down Del Harvey (the name she goes by, as you’ll read), who used to run the Trust and Safety team at Twitter:

»

LG: Do you generally believe the platforms should be arbiters of truth?

DH: I generally feel as though it is impossible and also that they have to try. It’s really true. You are never going to be able to fully succeed. You’re never going to be able to keep all bad things from happening.

I consistently had conversations with people … because people would go into trust and safety because they care, right? You don’t go into trust and safety because you’re like, “I enjoy getting praised for my work.” You really have to want to get into the weird, human, messy issues where sometimes both parties are at fault, sometimes neither party’s at fault, and you still have to navigate all of those.

I would tell this apocryphal story of this little boy who’s walking on the beach and there’s all these starfish that are stranded on the beach, trying to get back to the ocean before they die. And he’s walking along the beach, and every time he comes to a starfish, he’s picking up the starfish and he’s throwing it back in the water. And this guy comes along and asks, “What are you doing? There’s no point in doing that. There are literally thousands of starfish on this beach. You are never going to be able to make a difference here.” And the boy picks up the next starfish and tosses it into the ocean and says, “Made a difference to that one.”

«

I knew and liked Harvey through her role at Twitter. It’s a thorough interview, and – as is typical with her – she points out all the nuance and complication around content moderation.
unique link to this extract

China engineers complete largest solar farm on Earth in UAE ahead of Cop28 • South China Morning Post

Ling Xin:

»

The world’s largest single-site solar power plant – a flagship project under China’s Belt and Road Initiative – has been completed in the United Arab Emirates, ahead of the UN climate change conference Cop28 in Dubai later this month.

The two-gigawatt Al Dhafra Solar Photovoltaic Project covers 20 sq km (12.4 square miles) of desert outside Abu Dhabi and can power about 200,000 households, according to main contractor China National Machinery Industry Corporation.

The company said the plant was expected to help Abu Dhabi reduce carbon emissions by 2.4m tonnes each year – the equivalent of taking more than half a million cars off the road – and take the proportion of clean energy to over 13% of the emirate’s overall consumption.

By mid-November, the solar farm had already produced 3.6bn kilowatt-hours of clean electricity ahead of its official inauguration last Thursday.

…The plant consists of four million solar panels that can capture sunlight on both sides, according to the company, which was responsible for its design, civil engineering, equipment supply, installation and commissioning. It will also provide two years of operation and maintenance.

According to Chinese media reports, the three-year construction contract was signed in October 2020 – with the project team battling the Covid-19 pandemic and subsequent supply-chain constraints to complete the project on time.

«

Typical CCGT plants in the US are less than 1GW.
unique link to this extract

Turn speech into text with Audio Hijack 4.3’s new Transcribe block • Rogue Amoeba

Paul Kafasis:

»

Our flagship recording tool Audio Hijack can now act as your own personal stenographer! We’ve just released version 4.3, with a brand-new Transcribe block to turn spoken audio into a written text transcript.

…Transcribe can convert speech from an astonishing 57 languages into text, providing you with a written transcript of any spoken audio. It’s powered by OpenAI’s automatic speech recognition system Whisper, and features two powerful models for fast and accurate transcriptions.

Best of all, unlike traditional transcription services, Transcribe works for free inside of Audio Hijack. There’s absolutely no ongoing cost, so you can generate unlimited transcriptions and never again pay a per-minute charge. It’s pretty incredible.

It’s also completely private. When you use Transcribe, everything happens right on your Mac. That means your data is never sent to the cloud, nor shared with anyone else.

«

Whisper is open source, so Rogue Amoeba has incorporated it into its Mac app. You can get it to transcribe podcasts, interviews, or whatever is generating sound on a Mac, because Rogue Amoeba has a plugin which can capture sound from any application. Doesn’t need to be live sound either. Real-time transcription? This is very much what journalists have been wishing for for years.

(Fun story: Rogue Amoeba would be long dead if Steve Jobs hadn’t heard that podcasters needed it, and so told the RIAA – which wanted to squash it – to sod off.)
unique link to this extract

Giant batteries drain economics of gas power plants • Reuters via Yahoo

Sarah McFarlane and Susanna Twidale:

»

The long-term economics of gas-fired plants, used in Europe and some parts of the United States primarily to compensate for the intermittent nature of wind and solar power, are changing quickly, according to Reuters’ interviews with more than a dozen power plant developers, project finance bankers, analysts and consultants.

They said some battery operators are already supplying backup power to grids at a price competitive with gas power plants, meaning gas will be used less.

The shift challenges assumptions about long-term gas demand and could mean natural gas has a smaller role in the energy transition than posited by the biggest, listed energy majors.

In the first half of the year, 68 gas power plant projects were put on hold or cancelled globally, according to data provided exclusively to Reuters by US-based non-profit Global Energy Monitor.

Recent cancellations include electricity plant developer Competitive Power Ventures decision announced in October to abandon a gas plant project in New Jersey in the United States. It cited low power prices and the absence of government subsidies without giving financial detail.

British independent Carlton Power dropped plans for an £800m ($997m) gas power plant in Manchester, northern England, in 2016. Reflecting the shift in economics in favour of storage, this year it launched plans to build one of the world’s largest batteries at the site.

«

Once gas power plants start to be shunned in favour of renewables, things are really changing.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Car parks in Britain that require parking apps will soon be given a unique number to identify them. But what system should be used to number them? You could help. CC-licensed photo by Elliott Brown on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

It’s Friday, so there’s another post due at the Social Warming Substack at about 0845 UK time.

A selection of 11 links for you. Which app? I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Reflecting on 18 years at Google • Hixie’s Natural Log

Ian Hickson joined Google in 2005, just after the IPO:

»

My team was nominally the open source team at Google, but I was entirely autonomous (for which I owe thanks to Chris DiBona). Most of my work was done on a laptop from random buildings on Google’s campus; entire years went by where I didn’t use my assigned desk.

In time, exceptions to Google’s cultural strengths developed. For example, as much as I enjoyed [ex-Microsoft] Vic Gundotra’s enthusiasm (and his initial vision for Google+, which again was quite well defined and, if not necessarily uniformly appreciated, at least unambiguous), I felt less confident in his ability to give clear answers when things were not going as well as hoped. He also started introducing silos to Google (e.g. locking down certain buildings to just the Google+ team), a distinct departure from the complete internal transparency of early Google.

Another example is the Android team (originally an acquisition), who never really fully acclimated to Google’s culture. Android’s work/life balance was unhealthy, the team was not as transparent as older parts of Google, and the team focused on chasing the competition more than solving real problems for users.

…Then Google had layoffs. The layoffs were an unforced error driven by a short-sighted drive to ensure the stock price would keep growing quarter-to-quarter, instead of following Google’s erstwhile strategy of prioritising long-term success even if that led to short-term losses (the very essence of “don’t be evil”). The effects of layoffs are insidious. Whereas before people might focus on the user, or at least their company, trusting that doing the right thing will eventually be rewarded even if it’s not strictly part of their assigned duties, after a layoff people can no longer trust that their company has their back, and they dramatically dial back any risk-taking.

…It’s definitely not too late to heal Google. It would require some shake-up at the top of the company, moving the centre of power from the CFO’s office back to someone with a clear long-term vision for how to use Google’s extensive resources to deliver value to users. …I do think the clock is ticking, though.

«

unique link to this extract

An important parking infrastructure decision is about to be made – and I feel like us nerds can help make it right • Odds And Ends Of History

James O’Malley on plans afoot inside the Department of Transport, which aims to unify parking apps into a single system, but which then needs to uniquely identify every car park:

»

So here’s the challenge: can you come up with the best way to structure and allocate car park numbers?

I’m told that there will be some key design constraints the final system will need to follow:

• It will need to be numbers only, so that less-tech savvy people can type the numbers on old-fashioned phone keypad when calling to pay for parking
• The largest local authorities have more than 1,000 car parks, but fewer than 10,000, so will need to work with those sorts of numbers in each council area
• Parking codes will be dished out to local authorities in blocks or groups

And for reference, the parking industry is currently kicking around a bunch of ideas that include:

• The numbers could encode some sort of geographic reference (like phone numbers with area codes, or how postcodes contain postal distract letters at the start)
• The system will eventually handle different types of parking (on-street and off-street), and different types of payments (eg, pay before, pay on exit, EV-charging), so some existing proposals include a way of identifying this from the numbers used
• There’s also also lots of complexity in how parking is managed in different places, so there’s some debate over whether codes should reflect geography or owners (eg, a council or a company like NCP).

…So what’s the best way to do it? How many digits should it have? Can you think of some really clever way to encode geography into the numbers? Could the numbers include anything else, like a ‘type’ marker for, eg, car parks at train stations? Is there a rational way to allocate numbers for thousands of car parks that have arisen organically? How would you do it?

«

Seems like a challenge we can rise to! (Grammar note for James: “we nerds”, not “us nerds”.) My initial thought was to have both an “operator” and “geography” field. Trouble is, that could lead to pretty long numbers: there are sure to be more than 100 operators (ergo four-figure number) and perhaps 10,000 geographical regions. Already too long for poking into a smartphone on a cold wet Monday night.

So do something more like the mobile phone numbering system, which is also allocated in blocks, and manages to waste two digits (07) yet give everyone in the country a unique number. Sorted.

Let James know your solution in the comments of his post – else Those Who Matter won’t know.
unique link to this extract

Congrats to Elon Musk: I didn’t think you had it in you to file a lawsuit this stupid. But, you crazy bastard, you did it! • Techdirt

Mike Masnick has some fun tearing apart Elon Musk’s “nuclear” lawsuit against Media Matters for pointing out that some big-name brands could find their ads placed alongside objectionable content on “exTwitter”, as Masnick calls it:

»

Honestly, this feels like what you get when you have a rich but legally ignorant dude who announces on a Friday that there will be a lawsuit on Monday and finally finds some terrible lawyers who are actually willing to file something just to live up to that promise.

It’s not a good lawsuit. It’s barely even a lawsuit at all.

«

And he takes it apart thoroughly. (Thanks Terry for the link.) As a followup, people are debunking Musk’s claims by sending him screenshots in real time on his site.
unique link to this extract

About that OpenAI “breakthrough” • Marcus on AI

Gary Marcus on the Reuters story that OpenAI had a “breakthrough” with something called Q* which got the board a-flutter and worried:

»

I have seen this movie before, often.

OpenAI could in fact have a breakthrough that fundamentally changes the world.

But “breakthroughs” rarely turn to be general to live up to initial rosy expectations. Often advances work in some contexts, not otherwise. Arguably every putative breakthrough in driverless cars has been of this sort; somebody finds something new, it looks good at first, maybe even helps a bit, but at the end of the day, “autonomous” cars still aren’t reliable enough for prime time; no breakthrough has gotten us over the threshhold. AV’s still aren’t general enough that you can just plop down a car that was tuned in pilot studies in Menlo Park, SF and Arizona and expect it to drive gracefully and safely in Sicily or Mumbai. We are probably still many “breakthroughs” away from true level 5 driverless cars.

Or consider what was touted at OpenAI as an extraordinary breakthrough in 2019, when they launched a slick video and blog post about how they’d gotten a robot to solve a Rubik’s cube.

To many, the result sounded amazing. VentureBeat gullibly reported OpenAI’s PR pitch wholesale; “OpenAI — the San Francisco-based AI research firm cofounded by Elon Musk and others, with backing from luminaries like LinkedIn cofounder Reid Hoffman and former Y Combinator president Sam Altman — says it’s on the cusp of solving something of a grand challenge in robotics and AI systems.”

Me being me, I called bullshit, slamming OpenAI on Twitter a few days later.

Probably the most relevant bullet point on the right (at least for present purposes) was the one about generalization; getting their algorithm to work for one object (which, cheesily, turned out to be a special Cube instrumented with sensors and LEDS, unlike a Rubik’s cube you’d buy in a store) in carefully controlled lab circumstances hardly guaranteed that the solution would work more broadly in the complex open-ended real world.

«

Count him as a big sceptic on Q*, or at least a “show me first”.
unique link to this extract

Sonos readies $400-plus headphones to rival Apple and Bose, plus a TV set-top box • Bloomberg via Yahoo

Mark Gurman:

»

Sonos, best known for its smart speakers and sound bars, will make a long-awaited push into headphones with a model priced upwards of $400 that’s slated to be released as early as April, according to people familiar with the matter.

The company is also aiming to introduce a TV set-top box, which would compete with products from Apple and Roku, as early as the end of 2024, said the people, who asked not to be identified because the plans aren’t yet public. Sonos looks to charge between $150 and $200 for that device, which would run apps from popular streaming services.

The company is also developing new amplifiers and in-ceiling speakers aimed at professional installers, as well as a higher-end TV sound bar, new subwoofers, an update to the portable Roam speaker and a version of its Era 100 speaker for businesses. And it’s planning an updated voice control system, video service and upgraded smartphone app.

Sonos shares pared losses Tuesday on news of the product push. After falling nearly 4% earlier in the session, they were down 2% by the close in New York.

The new products are part of a bid by chief executive officer Patrick Spence to reignite growth at the audio technology company, which suffered a sales decline in the past year. Demand for smart speakers has cooled, and products like headphones are seen as an opportunity to leverage the Sonos brand to find a new moneymaker.

«

To be honest, it’s surprising that Sonos has held off on doing headphones for so long; Gurman says these have been in development since 2019, but repeatedly revised. The full article is essentially the company’s complete product roadmap for the next couple of years, so you could pick and choose what you think will sell, and what will be profitable. Headphones? Yes. Set-top box? Perhaps, but can’t see any profit in it. High-end soundbar? Sure, always a market for that. And so on.
unique link to this extract

Electric vehicle battery prices are falling faster than expected • Goldman Sachs

»

It wasn’t long ago rising demand and component shortages sparked concern that “greenflation” would drive up prices for the batteries used in electric vehicles. That’s subsiding as prices cool for battery metals, which could help make EVs more competitive with traditional cars more quickly. 

Goldman Sachs Research now expects battery prices to fall to $99 per kilowatt hour (kWh) of storage capacity by 2025 — a 40% decrease from 2022 (the previous forecast was for a 33% decline). Our analysts estimate that almost half of the decline will come from declining prices of EV raw materials such as lithium, nickel, and cobalt. Battery pack prices are now expected to fall by an average of 11% per year from 2023 to 2030, writes Nikhil Bhandari, co-head of Goldman Sachs Research’s Asia-Pacific Natural Resources and Clean Energy Research, in the team’s report.

As battery prices fall, Goldman Sachs Research estimates the EV market could achieve cost parity, without subsidies, with internal combustion engine (ICE) vehicles around the middle of this decade on a total-cost-of-ownership basis. 

«

There’s also a graph showing EV sales as a percentage of passenger car sales around the world: China leads by a long way at just over 25%, the EU is at 15+%, global average about 12.5%, and the US lagging at about 7.5%.

It’s not as if China is smaller than the US, so why isn’t range anxiety and the usual noises about charging a factor in China? Sales are about 2.5m per month there, compared to about 1.3m in the US. Is it because Chinese buyers are often getting their first car?
unique link to this extract

‘Squid Game: The Challenge’ players plan lawsuit over injury claims • Deadline

Jake Kanter:

»

Squid Game: The Challenge contestants are threatening legal action against Netflix and producers after claiming they were injured during the filming of the game show.

A British personal injuries law firm is representing two unnamed players who say they suffered hypothermia and nerve damage while shooting in cold conditions in the UK.

Express Solicitors said in a press statement that it had sent letters of claim to Studio Lambert, the co-producer of Netflix’s Squid Game: The Challenge.

The contestants’ allegations concern their experience shooting the show’s opening game ‘Red Light, Green Light,’ in which players must evade the attention of a menacing robotic doll.

The game was filmed at Cardington Studios, a former Royal Air Force base in Bedford, during a cold snap in Britain. Netflix confirmed at the time that three of 456 players required medical attention.

Express Solicitors, which specializes in no win no fee claims, said its clients risked their health by having to stay motionless for long periods during the shoot as they attempted to stay in the competition.

Daniel Slade, CEO of Express Solicitors, said: “We recognise people may see this as a classic David and Goliath battle with the company and its production partners. Contestants thought they were taking part in something fun and those injured did not expect to suffer as they did. Now they have been left with injuries after spending time being stuck in painful stress positions in cold temperatures.”

A spokesperson for Squid Game: The Challenge said: “No lawsuit has been filed by any of the Squid Game contestants. We take the welfare of our contestants extremely seriously.”

Deadline reported in February that Squid Game: The Challenge faced an independent safety inspection after the medical incidents on set.

«

As I recall from the original series, suffering from exposure would have been quite a good outcome after facing the “menacing robot doll”. I suspect that the Netflix release form will have covered this, as Netflix probably has the better lawyers. And did nobody watch Takeshi’s Castle? That was basically Squid Game but without the killing. Far more enjoyable.
unique link to this extract

Twitter bets big on … CEO’s son • Semafor

Max Tani:

»

Linda Yaccarino, the CEO of X, formerly Twitter, has turned the service’s Hail Mary bet on an imagined $100m political advertising business over to someone she trusts: her son Matt Madrazo.

Despite owner Elon Musk’s attempts to convert the company into a subscription-based service, the company remains dependent on an advertising business that produced about 90% of its revenue in 2021. And in the initial months after he bought Twitter, Musk expressed a keen interest in restarting the social media company’s political advertising business, which it had voluntarily shuttered in 2019.

In recent weeks, Madrazo, who previously headed ad sales at the non-political, creator-focused media firm Studio71, has been privately introducing himself to influential figures in the political ad world in Washington, D.C. He’s part of what’s essentially a two-man operation to restart X’s political advertising business with the goal of capitalizing on the massive amounts of money that campaigns are about to spend during the 2024 elections.

According to three people with knowledge of the situation, Madrazo has been tasked with outreach to Republican digital advertising firms and spenders. Jonathan Phelps, a Pandora and Univision veteran who also joined X in recent months, is handling the platform’s (far less promising) outreach to Democrats. Working occasionally out of Tesla’s D.C. offices, the duo are hoping to resuscitate a line of cash at a moment when the company is desperate for new revenue.

«

Which would be all well and dandy, except that in 2018, the last time Twitter ran political adverts, they brought in.. $3m. Out of $2.16 billion in revenue. How likely is it that that number will multiply 30-fold, even with a presidential election in the offing?
unique link to this extract

The end of anonymity on Chinese social media • Rest of World

Caiwei Chen:

»

On October 31, Weibo, as well as several other major Chinese social media platforms including WeChat, Douyin, Zhihu, Xiaohongshu, and Kuaishou, announced that they now required popular users’ legal names to be made visible to the public. Weibo stated in a public post that the new rule would first apply to all users with over 1 million followers, then to those with over 500,000.

Chinese social media users expressed criticism and concern over the new rule, with many saying it would violate user privacy, enable toxic online behaviors like doxxing and harassment, and limit the diversity of voices on the Chinese internet. Several famous online influencers, such as science blogger Ming Yu Zhui Ran, have decided to remove some of their followers to avoid making their identity public. Others, such as rapper Kindergarten Killer, have decided to delete their social media accounts altogether. (While Tu Pao Ding is still active on Weibo, her follower count was down to 219,700 at the time of publication.) 

When Cathy Zhang, a 33-year-old lifestyle blogger based in Shanghai, first saw a screenshot announcing Weibo’s new policy, she dismissed it as fake news. “It went against common sense, stripping away all anonymity from social media,” she told Rest of World. But the next day, she realized it was real: Weibo CEO Wang Gaofei’s profile now showed his real name and occupation, “mobile internet analyst.”

With a Weibo following of more than 35,000, Zhang has posted about wellness, and occasionally gender issues, on the platform for over 10 years, relying on her account to support herself financially. She has never posted her full name or identity online, which has partially shielded her from the hateful messages she often receives from online trolls. Although Zhang does not have enough followers to be affected by the new rule, she is worried. “I feel like I’ve just barely dodged a bullet,” she said.

«

The amazing thing is that China tolerated anonymity on social media at all. Though maybe it’s public anonymity, not anonymity from the authorities, that’s ending. The latter was probably never there.
unique link to this extract

Behind the scenes of Sam Altman’s showdown at OpenAI • WSJ

Keach Hagey, Deepa Seetharaman and Berber Jin:

»

People familiar with the [now mostly fired OpenAI] board’s thinking said there wasn’t one incident that led to their decision to eject Altman, but a consistent, slow erosion of trust over time that made them increasingly uneasy. Also complicating matters were Altman’s mounting list of outside AI-related ventures, which raised questions for the board about how OpenAI’s technology or intellectual property could be used. 

The board agreed to discuss the matter with their counsel. After a few hours, they returned, still unwilling to provide specifics. They said that Altman wasn’t candid, and often got his way. The board said that Altman had been so deft they couldn’t even give a specific example, according to the people familiar with the executives. 

The executives requested written examples of the board’s allegations.

Meanwhile, Altman was on the phone with Satya Nadella, the CEO of Microsoft, saying he wanted to keep working on the technology. They gamed out ways to undo the day’s events, but also began to hash out a backup plan for Altman to bring a bunch of his top researchers and start a new division at the tech giant, according to people familiar with their conversation. 

Altman also told friends that he was thinking of starting a new company with Brockman and intended to hire away dozens of OpenAI employees. 

Altman blamed himself for not better managing the board, which he felt was taken over by people overly concerned with safety and influenced by “effective altruism”. 

The specter of effective altruism had loomed over the politics of the board and company in recent months, particularly after the movement’s most famous adherent, Sam Bankman-Fried, the founder of FTX, was found guilty of fraud in a highly public trial. 

…Friday, after being fired, Altman immediately flew back to San Francisco. On Saturday, his Russian Hill home became a war room filled with OpenAI employees, including Murati, then the interim CEO, and other members of the executive team, plotting his return to the company.

They began to use X in a coordinated fashion for their campaign.

«

The board not quite being able to figure out what it was they objected to about Altman is the icing on the cake. The article is a little confusing in timeline (was Altman on the phone to Nadella on Friday, or Saturday?) but at its heart, this is about “effective altruism” (EA) v “effective acceleration” (e/acc): Altman’s from the latter tribe, wanting to zoom headlong into new technology, and figure out how to mop up the problems later.
unique link to this extract

ExxonMobil vs. Google: profits and perceptions explained • OilPrice.com

Robert Rapier:

»

Google’s net margin in Q3 was 22.5% (nearly double ExxonMobil’s) and its return on assets was 17.7% [v 11.1% for Exxon]. Google’s 2022 income bill was $11.4bn on net income of $60.0bn. Google shares trade at a price-to-earnings ratio (P/E ratio) of 20.5 based on earnings estimates for the next 12 months — nearly twice that of ExxonMobil.

So, Google makes more money on lower revenues and pays a lower overall tax rate than ExxonMobil. It has a net margin that is nearly double ExxonMobil’s. So why do people rage over ExxonMobil’s profits, but say absolutely nothing about Google’s?

The main reason is that we can see the direct impact of gasoline prices on our pocketbook, and we can’t really see how Google is impacting us. Thus, we feel like ExxonMobil is taking advantage, but we don’t feel the same way about Google.

Nevertheless, it should raise questions about what is an appropriate profit in a capitalistic society. Sure, Google and ExxonMobil are very different types of companies, but can you say what ExxonMobil’s profit margin should be? If I gave you ExxonMobil’s profit numbers, but told you it was for Starbucks or Apple or Nike, would you complain that it’s too much?

The reality is that the energy industry consistently ranks at or near the bottom of all sectors when it comes to profit margins. If you really think ExxonMobil is making too much money, then perhaps you could explain how much would be an “acceptable” amount, how you made that determination, and whether you apply that same standard to other corporations. And of course, you can always choose not to consume the company’s products and contribute to that profit.

«

Rapier contrasts Exxon’s profit, where he suggests it has no power over pricing (of oil – though OPEC’s cartel does control about 40% of crude oil production and price), with Google’s, where he suggests it does.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Despite having more than 500 million devices in homes, Amazon can’t get Alexa to turn a profit, and is cutting jobs. CC-licensed photo by ajay_suresh on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 11 links for you. Not that smart. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Exclusive: Sam Altman’s ouster at OpenAI was precipitated by letter to board about AI breakthrough -sources • Reuters

Anna Tong, Jeffrey Dastin and Krystal Hu:

»

Ahead of OpenAI CEO Sam Altman’s four days in exile, several staff researchers sent the board of directors a letter warning of a powerful artificial intelligence discovery that they said could threaten humanity, two people familiar with the matter told Reuters.

The previously unreported letter and AI algorithm was a catalyst that caused the board to oust Altman, the poster child of generative AI, the two sources said. Before his triumphant return late Tuesday, more than 700 employees had threatened to quit and join backer Microsoft in solidarity with their fired leader.

The sources cited the letter as one factor among a longer list of grievances by the board that led to Altman’s firing. Reuters was unable to review a copy of the letter. The researchers who wrote the letter did not immediately respond to requests for comment.

OpenAI declined to comment.

According to one of the sources, long-time executive Mira Murati told employees on Wednesday that a letter about the AI breakthrough called Q* (pronounced Q-Star), precipitated the board’s actions.

The maker of ChatGPT had made progress on Q*, which some internally believe could be a breakthrough in the startup’s search for superintelligence, also known as artificial general intelligence (AGI), one of the people told Reuters. OpenAI defines AGI as AI systems that are smarter than humans.

«

Murati has been one of the people pumping the brakes on OpenAI’s headlong rush towards AGI, as has chief scientist Ilya Sutskever. Both were influential in chucking Altman out last week. Draw your own conclusions. Certainly one of the hot take guesses last weekend was “OpenAI has invented AGI but Altman didn’t tell the board or try to slow it down, ergo defenestration”. Which maybe was close to right.

Anyway, perhaps this will be a hinge moment in human history. I for one welcome our new etc.
unique link to this extract

“ChatGPT with voice” opens up to everyone on iOS and Android • Ars Technica

Ron Amadeo:

»

It may have been a chaotic week at OpenAI, but the company has somehow still found time to roll out a product. “ChatGPT with voice” is available to free users of the ChatGPT app. This feature launched for paying users in September, and if you haven’t heard, it’s a full-blown voice assistant. The feature is still slowly rolling out to devices; on my Android phone, I don’t have a “headphone” icon anywhere, even with a Plus subscription.

When you have the feature, you can open the app, press the “headphone” icon, ask a question, and a stilted robot voice will read out a reply. It’s just like the voice assistants from Apple, Amazon, or Google, but this one is powered by a large language model. ChatGPT’s voice model is purely a question-and-answer type of voice assistant, though. Usually, these things are handy for what they can do on your behalf—make a phone call, control a smart home, take a note, or make a calendar appointment—but this can only answer questions.

«

“Hey, ChatGPT, exactly why was Sam Altman fired a week ago?”
unique link to this extract

Amazon to cut jobs at Alexa unit to sharpen focus on generative AI • Computerworld

Charlotte Trueman:

»

The company’s emphasis on developing generative AI systems has resulted in the release of new offerings, like the tool rolled out in September to generate copy listings for users selling items on the company’s e-commerce platform. The application is fuelled by a large language model (LLM) that Amazon has been developing internally,  originally to support the Alexa smart assistant.

But in a statement Monday, the company said its latest round of job cuts will impact staff working on Alexa-related efforts. “Several hundred roles are impacted, a relatively small percentage of the total number of people in the Devices business who are building great experiences for our customers.”

Amazon noted that there are more than half a billion Alexa devices in customers’ homes. “Our investments in generative AI are bringing our vision for an even more intuitive, intelligent, and useful Alexa closer than ever before,” the company said. “As we continue to invent, we’re shifting some of our efforts to better align with our business priorities, and what we know matters most to customers—which includes maximizing our resources and efforts focused on generative AI. These shifts are leading us to discontinue some initiatives, which is resulting in role eliminations.”

«

Half a billion devices in people’s homes, and yet can’t make money from them. That must be the definition of market failure.
unique link to this extract

Office landlords can’t get a loan anymore • WSJ

Konrad Putzier:

»

The office sector’s credit crunch is intensifying. By one measure, it’s now worse than during the 2008-09 global financial crisis.

Only one out of every three securitized office mortgages that expired during the first nine months of 2023 was paid off by the end of September, according to Moody’s Analytics. 

That is the smallest share for the first nine months of any year since at least 2008 and well below the nadir reached in 2009, when 47% of these loans got paid off. That share is also well below the rate before the pandemic, when more than eight out of every 10 maturing securitized office mortgages were paid back in some years. 

While the numbers cover only office mortgages packaged into bonds—so-called commercial mortgage-backed securities—they reflect a broader freeze in the lending market for office buildings.

Many office owners can’t pay back their old loans because they can’t get new mortgages. Remote work and rising vacancies have hit building profits, making it harder to pay interest. Higher interest rates have pushed debt costs up and building values down. 

That combination is fueling a rise in defaults. The share of office CMBS loans that are delinquent has tripled over the past year to 5.75%, according to Trepp. It doesn’t help that many banks no longer issue new office loans and that many insurance companies and debt funds have become more cautious.

“People just don’t want to touch it,” said Alex Killick, managing director at CWCapital, a company that handles troubled CMBS loans.

«

Quietly, very quietly, the post-pandemic effect begins to be felt.
unique link to this extract

Personal data stolen in British Library cyber-attack appears for sale online • The Guardian

Harriet Sherwood:

»

The British Library has confirmed that personal data stolen in a cyber-attack has appeared online, apparently for sale to the highest bidder.

The attack was carried out on October 31 by a group known for such criminal activity, said the UK’s national library, which holds about 14m books and millions of other items. Since then, the library’s website has been shut down, with updates posted on X and emailed to members

This week, Rhysida, a known ransomware group, claimed it was responsible for the attack. It posted low-resolution images of personal information online, offering stolen data for sale with a starting bid of 20 bitcoins (about £596,000).

Rhysida said the data was “exclusive, unique and impressive” and that it would be sold to a single buyer. It set a deadline for bids of 27 November.

The images appear to show employment contracts and passport information. The library said it was “aware that some data has been leaked, which appears to be from files relating to our internal HR information”. It did not confirm that Rhysida was responsible for the attack, nor that the data offered for sale was information on personnel.

Academics and researchers who use the library have been told that disruption to the institution’s services after the serious ransomware attack was likely to continue for months.

This week, the library advised its users to change any logins also used on other sites as a precaution. It added: “We have taken targeted protective measures to ensure the integrity of our systems, and we continue to undertake an investigation with the support of the National Cyber Security Centre (NCSC), the Metropolitan police and cybersecurity specialists. As this investigation remains ongoing, we cannot provide further details at this time.”

«

Personal details about librarians? Sure that will attract the big bidders. The puzzling point is why the Library hasn’t got some sort of backup of its databases. But as is so often the case, it’s only after you get hit by ransomware that you get smart about this stuff.
unique link to this extract

Where did they all go? How Homo sapiens became the last human species left • The Guardian

Sarah Wild:

»

What we do know is that from about 40,000 years ago, Homo sapiens was the last human standing out of a large and diverse group of bipedal hominins. Hypotheses range from benign, such as H sapiens having better infant survival rates than other hominins, or climate changes pushing other species to the brink. Others suggest a more active role, such as H sapiens hunting other humans or interbreeding with them and assimilating their genetics.

About 300,000 years ago, the first H sapiens populations were springing up in Africa. They didn’t look like modern humans, but they are more similar to us than other Homo species. They had tall, rounded skulls with an almost vertical forehead. They didn’t have the glowering brows of Neanderthals (Homo neanderthalensis) or the protruding jaw of archaic-looking species such as Homo naledi. They also had chins; something that no other Homo species has had (although we don’t know why only H sapiens has the protuberance).

A study published in Nature this year exploded the idea that H sapiens originated from a single place in Africa in one great evolutionary leap. By analysing the genomes of 290 people, the researchers showed that H sapiens descended from at least two populations that lived in Africa for 1m years, before merging in several interactions.

Palaeoanthropologists continue to argue (quite vociferously) over who the last ancestor of H Sapiens was, but so far there is no conclusive evidence. Also, there is no single origin for H sapiens. There are ancient remains of early H sapiens in Jebel Irhoud in Morocco, Omo Kibish in Ethiopia and Florisbad in South Africa, suggesting that our species arose from multiple sites.

When H sapiens moved out of Africa is also the subject of debate. Genetic evidence suggests there was a big foray out of the continent between 80,000 and 60,000 years ago. But it was not the first expedition. A perplexing H sapiens skull in Apidima in Greece has been dated to being at least 210,000 years old.

«

Our ancestry gets more and more complicated. Once it was just Neanderthals. Now it’s loads of rivals.
unique link to this extract

Inside the operation to bring down Trump’s Truth Social • WIRED

David Gilbert:

»

The North Atlantic Fella Organization (NAFO) is an online activist group founded last year to combat pro-Russia propaganda related to the invasion of Ukraine. Last month, the group turned its attention to Trump’s social network and launched a campaign to take over the trending topics section on the website. The group says that the operation, which included 50 “NAFO commandos,” as members targeting Truth Social call themselves, was so successful that those running the campaign now have a long-term goal: Take down Truth Social completely.

“The goal we have in mind, which is lofty, is to help bring the platform down ahead of the 2024 election,” Rock Kenwell, the pseudonymous leader of the NAFO commandos, tells WIRED. “We know it’s going to be an aggregator for extremism and probably violence the way things are looking at this point.”

Describing the Truth Social platform’s current environment, Kenwell compared the challenge of combating the spread of pro-Trump messaging on the platform with “dealing with your racist uncle that nobody wants at the Thanksgiving dinner table because he’s just obnoxious and looking to fight with everybody.”

Truth Social was launched in early 2022 by Trump, who had been kicked off of mainstream platforms for inciting violence. Trump claimed that the network would challenge “Big Tech platforms” like Facebook, Instagram, and Twitter as a free speech platform open to everyone, but in the 18 months since it started, the site has failed to attract anyone outside of Trump sycophants and QAnon conspiracy groups, and has instead become the butt of late night comedy. Last week, a filing to the US Securities and Exchange Commission (SEC) showed that the platform had lost $31m since it launched.

“It’s a very easy platform to manipulate. It’s a very primitive, social media environment,” adds Kenwell.

«

NAFO aims to take over the trending topics section, and claims to have done so with a campaign launched at the end of October which, it claims, led to the suspension of app downloads (to prevent new account registration). The next target is fake ads (though whether these are paid-for fake ads, or just posts that look like ads, isn’t clear.)

One has to wonder though if increasing the (apparent) engagement on the site is really the way you kill it it.
unique link to this extract

Inside Linda Yaccarino’s X all-hands after Elon Musk sued Media Matters • Fortune

Kylie Robison:

»

At the staff meeting Monday, one anonymous employee asked Yaccarino what she would consider the best outcome of the lawsuit [against MEdia Matters]. Yaccarino responded that it “would be the validation that Media Matters, unfortunately manipulates, in this case, not just advertisers but people in general.”

“Sunlight is the best disinfectant. Hopefully this is a disinfectant that surfaces all the great work that all of us are doing at X,” she said.

Both Musk and Yaccarino have defended X on the social media platform in the wake of the report. Musk claimed on Saturday that the watchdog group “created an alternate account and curated the posts and advertising appearing on the account’s timeline to misinform advertisers about the placement of their posts.”

Yaccarino reiterated many of the details in Musk’s post on Monday, telling staff that “this was a contrived experience that could be curated—or this situation could be committed—on any platform today.”

“No platform is gonna get it right,” Yaccarino said. “So they basically gamed the system.”

The X chief executive also sought to calm worries about the advertiser exodus, claiming some brands still doing business with X have told her that they believe that X “is vital for the global community” but want Yaccarino to share more data so they can explain their positions to employees and key stakeholders.

“They know that I work hard on their behalf and that I am a truth teller, and I want them to hear it from me—everything that is going on at the company,” Yaccarino, who has been in the advertising business for several decades, told staff. “And I tell a lot of people this: I didn’t come to the company because I needed the company. I came to the company because I wanted to help lead X and be successful in what we’re trying to achieve here.”

As big brands have paused ads on X, numerous right-wing media companies and influencers have pledged to advertise on X in order to make up for lost revenue. One anonymous staffer asked what should “we do as employees to be more responsible … just to help offset anything that we might be seeing from a loss from advertisers?”

Yaccarino responded that staff should “be as fiscally responsible as possible,” including only expensing “critical and necessary travel.”

«

From my experience at multiple organisations, when the chief exec tells the rank and file to be very careful with the travel expenses, things are financially going very badly.
unique link to this extract

Commercial flights are experiencing ‘unthinkable’ GPS attacks and nobody knows what to do • Vice

Matthew Gault:

»

In late September, multiple commercial flights near Iran went astray after navigation systems went blind. The planes first received spoofed GPS signals, meaning signals designed to fool planes’ systems into thinking they are flying miles away from their real location. One of the aircraft almost flew into Iranian airspace without permission. Since then, air crews discussing the problem online have said it’s only gotten worse, and experts are racing to establish who is behind it.

OPSGROUP, an international group of pilots and flight technicians, sounded the alarm about the incidents in September and began to collect data to share with its members and the public. According to OPSGROUP, multiple commercial aircraft in the Middle Eastern region have lost the ability to navigate after receiving spoofed navigation signals for months. And it’s not just GPS—fallback navigation systems are also corrupted, resulting in total failure.

According to OPSGROUP, the activity is centered in three regions: Baghdad, Cairo, and Tel Aviv. The group has tracked more than 50 incidents in the last five weeks, the group said in a November update, and identified three new and distinct kinds of navigation spoofing incidents, with two arising since the initial reports in September. 

While GPS spoofing is not new, the specific vector of these new attacks was previously “unthinkable,” according to OPSGROUP, which described them as exposing a “fundamental flaw in avionics design.” The spoofing corrupts the Inertial Reference System (IRS), a piece of equipment often described as the “brain” of an aircraft that uses gyroscopes, accelerometers, and other tech to help planes navigate.

«

Nobody knows who’s doing it (Syria is a suspect) nor why. Not very encouraging; the sort of thing that could accidentally cause a serious international incident if crews aren’t careful.
unique link to this extract

Behold the Ozempic effect on business • FT

Rana Foroohar:

»

Let’s start with the pharmaceutical firms themselves. If you don’t have an Ozempic knock-off in the development pipeline, your share price may take a hit. Novo Nordisk now has a market capitalisation that is higher than the entire GDP of Denmark, and Eli Lilly’s share price is up 40% since it rolled out its own weight-loss copycat Mounjaro. But both Pfizer and Moderna — neither of which have a successful semaglutide on the market — have seen their share prices plummet in recent months.  

And it’s not only companies in the weight-loss business that are being affected. In early October, when Novo Nordisk announced that Ozempic was so effective against kidney disease that it was stopping a trial early, shares in some dialysis providers tanked.

Now, healthcare analysts say that the $250bn cardiovascular disease market could be reduced by 10% by 2050, and hundreds of billions-worth of additional business in treatments for diabetes, kidney and liver disease and other weight related illnesses could be disrupted. 

The Ozempic effect doesn’t stop there. Analysts have downgraded doughnut maker Krispy Kreme recently amid worries that Americans on semaglutides just won’t reach for as many sweet treats as they have in the past.

…The new weight-loss drugs will also disrupt the US healthcare system — the only question is how. Semaglutides are expensive, but so is obesity.

One study found that obesity adds $1,861 in annual healthcare costs per American. But if the government decided that Medicare should reimburse for weight-loss drugs (it currently doesn’t) that would create huge costs, too. Insurance companies have long complained about obesity-related costs, but also don’t like the idea of tens of millions of Americans suddenly going on semaglutides.

«

unique link to this extract

From Napoleon to Elon Musk • The Bluestocking

Helen Lewis has put a transcript on her excellent Substack (you surely must subscribe) of a conversation she had with David Runciman, professor of politics at Cambridge University, about his new book The Handover which is about “the similarities between states, corporations and AIs”. It’s all excellent, though this passage jumped out at me:

»

David Runciman: The great appeal of AI systems, particularly for states and corporations, is their efficiency—and what they mean by “efficiency” is they strip out human error.

But in warfare, mutually assured destruction is a game of chicken. The way you bypass that in a game of chicken is you strip out the human beings and make sure that it’s a robot that presses the button, because the robot won’t have qualms. China and America are currently involved in an arms race which is premised on this. The Chinese state is massively investing in AI weapons technology, precisely because in this great game of chicken that may be played over Taiwan, you want to signal to the other side that you’ve got fewer humans involved in your process than they do. 

Helen Lewis: There was a famous thought experiment once that said the nuclear code should be embedded in the heart of a bodyguard, who walks around with the president all the time. And if he wants to launch a nuclear weapon that will kill 80,000 people, maybe he first of all has to carve into the heart of the guy that’s been walking around with him.

David Runciman: You think Donald Trump wouldn’t do that?

«

unique link to this extract

Errata, corrigenda and ai no corrida: none notified

The time zone system in Windows 95 had a rather sizeable bug which would submerge Poland on demand. CC-licensed photo by 70023venus2009 on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 9 links for you. Wetsuit? I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

A dead friend seemed to contact me on Facebook. The truth was sadder • The Guardian

Akin Olla:

»

I burst into tears when my friend tagged me in another Facebook post this morning. My friend died in 2021. The bot or scammer that had taken over his account was using it to promote weight-loss pills, which felt particularly egregious considering my friend had lost weight before his sudden death; it was as if the bot had scraped his profile for the most marketable details before taking his place.

This was not the first time I’d been contacted on social media from beyond the grave. Earlier this year, my best friend messaged me; that time, too, it was deeply unsettling, since the last time I’d seen him, he was smiling at me from his open casket. As terrible as these uncanny experiences were for me, what really broke my heart was thinking of how my friends’ mothers were likely experiencing the same thing.

I suspect that these “ghost” social media experiences are going to be increasingly common in the coming years. Our profit-driven economic system pushes social media companies to digitize and monopolize our social lives. This same engine drives scammers to seek out every means of exploiting our weaknesses for their benefit. A good password today may not be secure in two or three years, let alone the decades by which our social media accounts may outlive us.

Most social media companies make their money by collecting our information and pipelining their ads right in between wedding announcements and baby pictures. They seek normal social activities, like sharing images or starting clubs, and replicate them online, making them accessible enough that we become reliant on their platforms. This reliance is made worse by algorithms that keep us hooked and clicking.

…Scammers are obligated to be good at their game, and are likely to get better. There are already plenty of means to crack people’s passwords, and new AI-powered tools threaten to exacerbate that. According to the cybersecurity company Avast, 83% of Americans have weak passwords as it is. I am, I suppose, lucky to know that my friends are actually dead.

…The more likely, and already somewhat present scenario, will be a social media hellscape littered with dead people pushing weight-loss pills and cryptocurrency schemes. Facebook has options to preserve accounts as memorials, but one study estimates that there are likely tens of millions of dead people on Facebook and there will likely be hundreds of millions by 2060.

«

unique link to this extract

OpenAI and Microsoft sued by nonfiction writers for alleged ‘rampant theft’ of authors’ works • Forbes

Rashi Shrivastava:

»

The lead plaintiff of the lawsuit is Julian Sancton, the New York Times-bestselling author of Madhouse at the End of the Earth: The Belgica’s Journey Into the Dark Antarctic. Sancton spent five years and tens of thousands of dollars traveling around the world to complete the research for the book, the lawsuit states. In response to a prompt, ChatGPT confirmed that Sancton’s book was a part of the dataset that was used to train the chatbot, according to the lawsuit filed by law firm Susman Godfrey LLP.

Sancton and thousands of other writers did not consent nor were compensated for the use of their intellectual property in the training of the AI, the lawsuit notes. Their complaint also highlights that Microsoft and OpenAI have commercialized their AI models, making billions of dollars in revenue through products like BingChat and ChatGPT Enterprise.

“Nonfiction authors often spend years conceiving, researching, and writing their creations. While OpenAI and Microsoft refuse to pay nonfiction authors, their AI platform is worth a fortune. The basis of the OpenAI platform is nothing less than the rampant theft of copyrighted works,” the lawsuit states.

«

As with all these, I don’t set much store on their succeeding because even if you do it as a class action, on behalf of everyone whose work has been used, the ingestion is permissible (same as reading a book) and the use is transformative (you don’t get the book out at the prompt).

Also: the OpenAI/Altman soap opera is still dragging on, and we still don’t know precisely why Altman was fired, though the board itself may be about to get fired.
unique link to this extract

CZ steps down as Binance CEO in $4bn settlement with DOJ • Semafor via Yahoo

Diego Mendoza:

»

Changpeng “CZ” Zhao, the billionaire founder of the world’s largest cryptocurrency exchange, Binance, has stepped down as CEO and pleaded guilty to money laundering charges as part of $4.3bn settlement with the U.S. Department of Justice, Attorney General Merrick Garland announced Tuesday.

Zhao will be personally required to pay $50m as part of the fines.

“The message here should be clear: using new technology to break the law does not make you a disruptor, it makes you a criminal,” Garland said at a press conference.

Prosecutors said that Binance enabled the financing of terrorist and militant groups like Hamas, the Palestinian Islamic Jihad, ISIS, and Al Qaeda through its exchange.

“Binance prioritized its profits over the safety of the American people,” Garland said.

The development comes months after the Securities and Exchange Commission (SEC) filed charges against the crypto giant for artificially inflating its trade volume on its US platform. The company also faces allegations of offering US citizens crypto derivatives, such as futures or options contracts, without registering as a futures commodity merchant. Kraken, another trading firm, was sued by the SEC on Monday for similar alleged violations.

Zhao is based in Dubai, which means he is unlikely to face prison time as the United Arab Emirates does not have an extradition agreement with the US.

«

Is this going to rattle confidence in crypto? Very much doubt it. CZ will swan around, and perhaps start up another crypto exchange which perhaps will ignore money laundering rules. The cycle continues.
unique link to this extract

That one time Windows accidentally sent Poland under the sea • The Register

Richard Speed:

»

Microsoft veteran Raymond Chen took to YouTube over the weekend to remind us of the time the Windows vendor accidentally sank Poland.

Speaking on the Dave’s Garage channel, run by former Microsoft engineer Dave Plummer, Chen added some flourishes to a story from decades ago regarding the neat time zone map that initially shipped with Windows 95.

Readers of a certain age might remember the original Windows 95 time zone map. It was a fun feature where a user could click on a region of a map to select a time zone or regional settings – something that engineers doubtless had a blast making before geopolitical realities hit home.

If you don’t remember the time zone map working that way, don’t worry. Microsoft had to pull the features after governments complained about where their borders were. In 2003, Chen explained: “In early 1995, a border war broke out between Peru and Ecuador, and the Peruvian government complained to Microsoft that the border was incorrectly placed. Of course, if we complied and moved the border northward, we’d get an equally angry letter from the Ecuadorian government demanding that we move it back. So we removed the feature altogether.”

Talking to Plummer, Chen added some more detail: “There were even arguments from countries who were not engaged in a border conflict where a small European country would contact us and say, ‘Hey, our country is kind of small, can you give us one of our neighbor’s pixels to make it easier to click on?”

This triggered an angry response from another country demanding why one of their pixels had been given away, and so it went on.

Since making everyone happy was impossible, Chen said the solution was to rotate the map to put the selected zone in the center. All good? Not quite…

“There was a bug that we introduced when we did that though…”

«

It’s quite a neat bug; essentially they got bitten by a version of the four-colour theorem.
unique link to this extract

Meta, Microsoft, Amazon join Overture maps to vie with Apple, Google • CNBC

Kif Leswing:

»

Google and Apple dominate the market for online maps, charging mobile app developers for access to their mapping services. The other mega-cap tech companies are joining together to help create another option.

A group formed by Meta, Microsoft and Amazon Web Services, along with TomTom, is releasing data that could enable companies to build their own maps, without having to rely on Google or Apple.

The Overture Maps Foundation, which was established late last year, captured 59 million “points of interest,” such as restaurants, landmarks, streets and regional borders. The data has been cleaned and formatted so it can be used for free as the base layer for a new map application.

Meta and Microsoft collected and donated the data to Overture, according to Marc Prioleau, executive director of the OMF. Data on places is often difficult to collect and license, and building map data requires lots of time and staff to gather and clean it, he told CNBC in an interview.

“We have some companies that, if they wanted to invest to build the map data, they could,” Prioleau said. Rather than spending that kind of money, he said, companies were asking, “Can we just get collaboration around the open base map?”

Overture is aiming to establish a baseline for maps data so that companies can use it to build and operate their own maps.

«

This appeared in July, perhaps while I was On A Break. It’s a bit puzzling: are they trying to create a commercial product, or just a rival? Because OpenStreetMap already exists. Why not contribute to that? An ex-Meta person says “Overture seeks to distinguish its data from OpenStreetMap’s by being more closely vetted and curated.”
unique link to this extract

Musk files lawsuit claiming Media Matters manipulated X by scrolling down • Ars Technica

Ashley Belanger:

»

Musk’s complaint—bizarrely filed in a Texas court despite X Corp. being based in Nevada and Media Matters in the District of Columbia—accused Media Matters of interference with X Corp.’s contract with advertisers, business disparagement, and interference with a prospective economic advantage by allegedly disrupting X Corp.’s relationship with advertisers.

The lawsuit’s business disparagement claim marks the first time that Musk has sued a group monitoring hate speech on X for defaming the platform. Where individuals can sue for defamation, businesses can sue over disparagement. In this case, Musk must prove that Media Matters knowingly published false statements intended to harm X Corp.’s business to succeed in his lawsuit.

According to X, Media Matters “took screenshots of posts from IBM, Apple, Bravo, Xfinity, and Oracle that Media Matters engineered to appear adjacent to inflammatory, fringe content.” All of these advertisers except Oracle, X confirmed, stopped advertising on X, as well as other advertisers whose ads weren’t even included in Media Matters’ report.

If the lawsuit proceeds, Musk may have a hard time proving that Media Matters published any false statements, though. X’s complaint alleged that Media Matters “manipulated” the platform’s algorithm to generate inorganic ad placements to form a “blatant smear campaign,” but the complaint seemingly admitted that no statements that Media Matters published were false. Media Matters will likely argue that advertisers could interpret its reporting however they felt would be best for their business.

«

Indeed, analysis by an independent lawyer on Twitter suggested that the lawsuit admits everything that Media Matters claims; it just insists that they’re not very common. That’s a problem for… Musk.
unique link to this extract

Does AI lead police to ignore contradictory evidence? • The New Yorker

Eyal Press:

»

Advocates of facial-recognition technology acknowledge that the quality of the algorithms varies greatly, but they contend that the best ones do not have such demographic imbalances. They also note that, among the millions of searches that have been conducted by police, only a few have been proved to lead to wrongful arrests. But how many people have been erroneously identified without the mistake being recognized?

Nobody can say, in part because the technology is poorly regulated and the police’s use of it is often not shared with either the public or the accused. Last fall, a man named Randal Quran Reid was arrested for two acts of credit-card fraud in Louisiana that he did not commit.

The warrant didn’t mention that a facial-recognition search had made him a suspect. Reid discovered this fact only after his lawyer heard an officer refer to him as a “positive match” for the thief. Reid was in jail for six days and his family spent thousands of dollars in legal fees before learning about the misidentification, which had resulted from a search done by a police department under contract with Clearview AI. So much for being “100% accurate.”

Law-enforcement officials argue that they aren’t obligated to disclose such information because, in theory at least, facial-recognition searches are being used only to generate leads for a fuller investigation, and do not alone serve as probable cause for making an arrest.

Yet, in a striking number of the wrongful arrests that have been documented, the searches represented virtually the entire investigation. No other evidence seemed to link Randal Reid, who lives in Georgia, to the thefts in Louisiana, a state he had never even visited.

«

Naturally, this leans heavily on Kashmir Hill’s book “Your Face Belongs To Us”, about Clearview AI.
unique link to this extract

“Make It Real” AI prototype wows devs by turning drawings into working software • Ars Technica

Benj Edwards:

»

[Last week] a collaborative whiteboard app maker called “tldraw” made waves online by releasing a prototype of a feature called “Make it Real” that lets users draw an image of software and bring it to life using AI. The feature uses OpenAI’s GPT-4V API to visually interpret a vector drawing into functioning Tailwind CSS and JavaScript web code that can replicate user interfaces or even create simple implementations of games like Breakout.

“I think I need to go lie down,” posted designer Kevin Cannon at the start of a viral X thread that featured the creation of functioning sliders that rotate objects on screen, an interface for changing object colors, and a working game of tic-tac-toe. Soon, others followed with demonstrations of drawing a clone of Breakout, creating a working dial clock that ticks, drawing the snake game, making a Pong game, interpreting a visual state chart, and much more.

Users can experiment with a live demo of Make It Real online. However, running it requires providing an API key from OpenAI, which is a security risk. If others intercept your API key, they could use it to rack up a very large bill in your name (OpenAI charges by the amount of data moving into and out of its API). Those technically inclined can run the code locally, but it will still require OpenAI API access.

«

We don’t know how secure the underlying code might be, but this is definitely taking drudgery out of the design process. Which then means that humans are free to do the more important, subtle changes, so this must be a benefit, correct?
unique link to this extract

US companies fight Biden’s efforts to crack down on junk fees • The Washington Post

Tony Romm:

»

Frustrated with airlines that charge passengers steep fees to check bags and change flights, President Biden last fall embarked on a campaign to crack down on the practice — and force companies to show the full price of travel before people pay for their tickets.

Fliers rejoiced, flooding the Department of Transportation with letters urging it to adopt the policy. Airlines including American, Delta and United, however, did not seem so enthused.

It would be too difficult to disclose the charges more clearly, warned Doug Mullen, the deputy general counsel at Airlines for America, an industry lobbying group representing the three carriers. Testifying at a federal hearing in March, he said the new policy would only cause customers “confusion and frustration” — and, besides, the extra costs for bags and other services historically have resulted in “very few complaints.”

“The department should not regulate in this area,” Mullen added.

Since then, the Biden administration has broadened its efforts to expose or eliminate “junk fees” throughout the economy, touching off a groundswell of opposition from airlines, auto dealers, banks, credit card companies, cable giants, property owners and ticket sellers that hope to preserve their profits.

Behind the scenes, these corporations have fought vigorously to thwart even the most basic rules that would require them to be more transparent about hidden charges, according to a Washington Post review of federal lobbying records and hundreds of filings submitted to government agencies. The fees together may cost Americans at least $64bn annually, according to a rough White House estimate, underscoring its efforts to deliver financial relief to families grappling with high prices.

«

What an absolutely colossal amount. “Very few complaints” about the extra costs? How would people complain, exactly? When? Is there an option in the drop-down menu for “pay for extra bag, and complain about it”? The irony is that the people who implement these things at the low level – the programmers and staff – are the ones who suffer from it when it’s done to them by every other company. War by different means. (A 2021 experiment showed that this method, applied to gig tickets, raises the price by 21%.)
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Gene editing is able to cure sickle cell disease, aka thalassemia, in a remarkable application of CRISPR technology. CC-licensed photo by scooterdmu on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

There’s another post coming this week at the Social Warming Substack on Friday at 0845 UK time. Free signup.

A selection of 10 links for you. Neatly edited. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Sam Altman is still trying to return as OpenAI CEO • The Verge

Alex Heath and Nilay Patel:

»

Sam Altman’s surprise move to Microsoft after his shock firing at OpenAI isn’t a done deal. He and co-founder Greg Brockman are still willing to return to OpenAI if the remaining board members who fired him step aside, multiple sources tell The Verge.

The promised mass exodus of virtually every OpenAI employee — including board member and chief scientist Ilya Sutskever, who led the initial move to depose Altman! — means that there is more pressure on the board than ever, with only two of the three remaining members needing to flip. Altman posted on X that “we are all going to work together some way or other,” which we are told is meant to indicate that the fight continues.

Altman, former president Brockman, and the company’s investors are still trying to find a graceful exit for the board, say multiple sources with direct knowledge of the situation. The sources characterized the hiring announcement by Microsoft, which needed to have a resolution to the crisis before the stock market opened on Monday, as a “holding pattern.”

A spokesperson for Microsoft declined to comment.

After Altman was suddenly fired on Friday, negotiations with the board to potentially bring him back reached a stalemate.

«

It’s still all up in the air. At the time of compilation, about 95% of OpenAI’s staff had signed an open letter basically telling the OpenAI board they’re idiots. Among the signatories was Sutskever, which is the most absurd thing I’ve ever seen: signing a letter saying two-days-ago-you is an idiot.

Ben Thompson points out that Microsoft will either acquire OpenAI’s staff, or the company. Big winner: Microsoft. Satya Nadella, its CEO, says the oversight of OpenAI needs to change (perhaps put its biggest investor, in effect Microsoft, on the board?). And an analysis of the boards of not-for-profits (such as OpenAI) says “their governance is generally abysmal”.

Plus (at time of compilation) we still don’t know precisely why Altman was fired.
unique link to this extract

Portugal just ran on 100% renewable energy for six days • JOE.co.uk

Joseph Loftus:

»

Portugal has reportedly broke a record for energy production after going six days relying entirely on renewable energy.

This apparently includes everything from electrical applianes in home and work, all were running on either wind, hydro, or solar power for six days straight.

Between 4:00AM on 31 October and 9:00AM on 6 November, the nation of ten million relied on only renewable energy, as 1102 GWh was generated.

Hugo Costa, the individual who runs EDP Renewables, the country’s renewable arm of the state utility, said: “The gas plants were there, waiting to dispatch energy, should it be needed. It was not, because the wind was blowing; it was raining a lot. And we were producing with a positive impact to the consumers because the prices have dropped dramatically, almost to zero.”

The news comes as many nations across Europe attempt to hit the Paris Agreement’s climate goals by 2050.

When 2050 finally comes around, nations need not only run via renewable energy for six days, but all year round.

«

Not so sure about that last sentence. “Net zero” means what it says: net, not totally, zero.

As a comparison, the UK’s electricity system uses an average of 715GWh per day; Portugal seems to consume about 184GWh per day. In the UK, wind generates about 10-15GW, or 240-360GWh per day. It’s just a question of scaling up.
unique link to this extract

Apple plans to equip MacBooks with in-house cellular modems • MacRumors

Tim Hardwick:

»

Apple has reportedly been working on its own modem since 2018, as it seeks to move away from Qualcomm’s component currently used in iPhones. The timeframe for launching the modem has slipped several times and is now expected to be ready around 2026, and Gurman now hears that Apple has plans for the chip appearing in other Apple devices further down the line.

Writing in his latest Power On newsletter, Gurman says that Apple’s custom technology aspirations include integrating an in-house modem into its system-on-a-chip (SoC), which would eventually see the launch of MacBooks with built-in cellular connectivity.

Gurman says Apple will “probably need two or three additional years to get that chip inside cellular versions of the Apple Watch and iPad – and the Mac, once the part is integrated into the company’s system-on-a-chip.”

Apple has explored the possibility of developing MacBooks with cellular connectivity in the past. Indeed, the company reportedly considered launching a MacBook Air with 3G connectivity, but former CEO Steve Jobs said in 2008 that Apple decided against it, since it would take up too much room in the case. An integrated SoC would solve that problem.

«

At least Marco Arment and Casey Liss will be happy. (They’ve wanted modems in laptops for ages. Amusingly, in the early days of the internet, laptops did come with modems: it was how you got online.)

Apple won’t have wanted to use Qualcomm’s modems because Qualcomm charges a percentage of the product’s retail price. If Apple only uses Qualcomm’s patents, that’s a lot cheaper.
unique link to this extract

The world’s 280 million electric bikes and mopeds are cutting demand for oil far more than electric cars • The Conversation

Muhammad Rizwan Azhar and Waqas Uzair:

»

Close to half (44%) of all Australian commuter trips are by car – and under 10km. Of Perth’s 4.2 million daily car trips, 2.8 are for distances of less than 2km.

This is common in wealthier countries. In the United States, a staggering 60% of all car trips cover less than 10km.

So what’s the best solution? You might think switching to an electric vehicle is the natural step. In fact, for short trips, an electric bike or moped might be better for you – and for the planet. That’s because these forms of transport – collectively known as electric micromobility – are cheaper to buy and run.

But it’s more than that: they are actually displacing four times as much demand for oil as all the world’s electric cars at present, due to their staggering uptake in China and other nations where mopeds are a common form of transport.

On the world’s roads last year, there were over 20 million electric vehicles and 1.3 million commercial EVs such as buses, delivery vans and trucks.

But these numbers of four or more wheel vehicles are wholly eclipsed by two- and three-wheelers. There were over 280 million electric mopeds, scooters, motorcycles and three-wheelers on the road last year. Their sheer popularity is already cutting demand for oil by a million barrels of oil a day – about 1% of the world’s total oil demand, according to estimates by Bloomberg New Energy Finance.

What about electric vehicles, you ask? After all, EVs have been heralded as a silver bullet for car emissions and air pollution in cities, as their tailpipe emissions are zero. If charged with renewable power, they get even greener.

But to see them as an inarguable good is an error. They are cleaner cars, but they are still cars, taking up space on the roads and requiring a lot of electricity to power them.

«

Only thing is: what about when it rains?
unique link to this extract

AI scam calls: This mom believes fake kidnappers cloned her daughter’s voice • CNN

Faith Karimi:

»

Jennifer DeStefano’s phone rang one afternoon as she climbed out of her car outside the dance studio where her younger daughter Aubrey had a rehearsal. The caller showed up as unknown, and she briefly contemplated not picking up.

But her older daughter, 15-year-old Brianna, was away training for a ski race and DeStefano feared it could be a medical emergency. “Hello?” she answered on speaker phone as she locked her car and lugged her purse and laptop bag into the studio.

She was greeted by yelling and sobbing. “Mom! I messed up!” screamed a girl’s voice.

“What did you do?!? What happened?!?” DeStefano asked.

“The voice sounded just like Brie’s, the inflection, everything,” she told CNN recently. “Then, all of a sudden, I heard a man say, ‘Lay down, put your head back.’ I’m thinking she’s being gurnied off the mountain, which is common in skiing. So I started to panic.”

As the cries for help continued in the background, a deep male voice started firing off commands: “Listen here. I have your daughter. You call the police, you call anybody, I’m gonna pop her something so full of drugs. I’m gonna have my way with her then drop her off in Mexico, and you’re never going to see her again.”

DeStefano froze. Then she ran into the dance studio, shaking and screaming for help. She felt like she was suddenly drowning. After a chaotic, rapid-fire series of events that included a $1m ransom demand, a 911 call and a frantic effort to reach Brianna, the “kidnapping” was exposed as a scam. A puzzled Brianna called to tell her mother that she didn’t know what the fuss was about and that everything was fine.

But DeStefano, who lives in Arizona, will never forget those four minutes of terror and confusion – and the eerie sound of that familiar voice. “A mother knows her child,” she said later. “You can hear your child cry across the building, and you know it’s yours.”

«

There’s a fair amount of doubt around this story: can AI voice copying really simulate screams, yelling, sobbing? Though free apps can clone a voice in a minute.

Generally, these sorts of calls are becoming common (or less uncommon) in the US, and of course the WhatsApp scams which don’t need voice are all over the place. Take Rob Leathern’s advice: work out a “safe word” for live calls, and a different one for a recording.
unique link to this extract

Sickle-cell treatment created with gene editing wins UK approval • The New York Times

Gina Kolata:

»

Regulators in Britain [last week] approved the first treatment derived from CRISPR, the revolutionary gene-editing method. Called Casgevy, the treatment is intended to cure sickle-cell disease and a related condition, beta thalassemia.

The manufacturers, Vertex Pharmaceuticals, based in Boston, and CRISPR Therapeutics, based in Switzerland, say about 2,000 patients in Britain with sickle-cell disease or beta thalassemia are expected to be eligible for the treatment.

The companies anticipate that the Food and Drug Administration (FDA) will approve Casgevy for sickle-cell patients in the United States in early December. The agency will decide on approval for beta thalassemia next year.

In late December, the FDA is expected to approve another sickle cell gene therapy by Bluebird Bio of Somerville, Mass. That treatment does not rely on gene editing, instead using a method that inserts new DNA into the genome.

Sickle-cell disease is caused by a defective gene that leads to the creation of abnormal hemoglobin, the oxygen-carrying component in red blood cells. The cells themselves become malformed, causing episodes of extreme pain. About 100,000 Americans, who are mostly Black and Hispanic, are believed to have the illness.

…Casgevy relies on CRISPR to nick the DNA, activating a gene that produces an alternative form of hemoglobin. To receive the sickle-cell treatment, patients in Britain must be at least 12 years old and have experienced repeated episodes of extreme pain.

There is no upper age limit, nor are patients excluded because they have suffered too much organ damage from sickle-cell disease, said Dr. David Altshuler, Vertex’s chief scientific officer.

But the patients must have no other options. Sickle-cell disease can be cured with a bone-marrow transplant, but few patients have compatible donors.

«

Expensive, and there’s a (relatively) cheaper alternative – bone marrow transplant – but for that you need donors.
unique link to this extract

US is seeking more than $4bn from Binance to end case • Bloomberg via Yahoo

Chris Strohm, Allyson Versprille and Olga Kharif:

»

Negotiations between the Justice Department and Binance include the possibility that its founder Changpeng Zhao would face criminal charges in the US under an agreement to resolve the probe into alleged money laundering, bank fraud and sanctions violations, according to people familiar with the discussions.

Zhao, also known as “CZ,” is residing in the United Arab Emirates, which doesn’t have an extradition treaty with the US, but that doesn’t prevent him from coming voluntarily.

Binance didn’t respond to multiple emails and phone calls seeking comment. The Justice Department declined to comment.

An announcement could come as soon as the end of the month, though the situation remains fluid, according to the people, who asked not to be named discussing a confidential matter.

The BNB cryptocurrency, a token native to Binance and the BNB Chain blockchain that was created by the exchange, rose as much as 8.5% to $266.42 after Bloomberg reported the negotiations.

«

Incredible if a cryptocurrency exchange happened to have that sort of money lying around that actually belongs to it. However this is only the DoJ – the SEC filed suit in June alleging mishandling of customer funds, misleading investors and breaking securities rules. The DoJ complaint is about money laundering, bank fraud and sanctions violations. None of it is what you’d call minor.
unique link to this extract

Global warming on track for 2.9ºC as greenhouse gases keep rising, UN says • FT

Kenza Bryan and Steven Bernard:

»

The world is on track for a temperature rise of up to 2.9ºC above pre-industrial levels, a report by the UN environment programme has found, even assuming countries stick to their Paris agreement climate pledges.

UN chief António Guterres said that keeping the Paris goal of limiting the rise to ideally 1.5ºC and well below 2ºC would require “tearing out the poisoned root of the climate crisis: fossil fuels.”

“Otherwise, we’re simply inflating the lifeboats while breaking the oars,” he added. The world has already warmed by at least 1.1ºC.

Coming ahead of the COP28 climate summit in Dubai in 10 days, the latest UN report estimated the size of the gap between the emissions trajectory implied by climate pledges and the one needed to limit warming,

The level of greenhouse gas emissions stood at a new peak of 57.4bn tonnes of carbon dioxide equivalent, the UN emissions gap report noted, after rising 1.2% from 2021 to 2022.

Guterres referred to this “gap” as a “canyon littered with broken promises, broken lives, and broken records.”

Emissions cuts of 14bn tonnes or 28% are needed by 2030 to keep within 2ºC of warming, and a more ambitious reduction of more than 40% or 22bn tonnes is needed for the 1.5ºC threshold to be realistic.

«

This is what we need a time machine for: to take us back so that we can get things on the right track much earlier. More wind farms, more nuclear power plants.
unique link to this extract

Patrick Vallance contradicts Rishi Sunak’s evidence to Covid inquiry • The Guardian

Peter Walker:

»

Rishi Sunak would almost certainly have known scientists were worried about his “eat out to help out” scheme during the pandemic, Sir Patrick Vallance has said, directly contradicting the prime minister’s evidence to the Covid inquiry.

In potentially damaging testimony, Vallance, the UK government’s chief scientific adviser during the pandemic, said he would be “very surprised” if Sunak, then chancellor, had not learned about objections to his plan to help the hospitality industry.

Sunak had written to the inquiry saying he “[did] not recall any concerns about the scheme” being raised in ministerial meetings despite growing concerns that the discount plan could fuel the spread of the virus.

An extract from Vallance’s contemporaneous diary, in July 2020, provided evidence that Sunak also sought to push back against the scientists’ advice. In one economics-based meeting, Sunak said “it’s all about handling the scientists, not handling the virus”, the entry said.

Vallance said: “There were definitely periods when it was clear that the unwelcome advice we were giving was, as expected, not beloved, and that meant we had to work doubly hard to make sure that the science evidence and advice was being properly heard.”

«

Philip Ball, a science writer, wrote a thread on this, beginning: “I can’t see how Eat Out To Help Out can’t now become a major scandal. Here was a scheme imposed by Sunak with zero scientific consultation, and which in Vallance’s words utterly reversed the public-health messaging: from “Keep distant from those outside your family” to “We’ll pay you to spend hours in an enclosed space with people you don’t know.” Sunak, he suggests, misled the inquiry over this.
unique link to this extract

The cassette-tape revolution • The New Yorker

Jon Michaud:

»

The compact audiocassette (to give it its full name) was conceived by Lou Ottens, the head of product development at the Dutch electronics company Phillips. One day, in the early nineteen-sixties, frustrated after “fiddling with that damn reel-to-reel” (as a colleague later recalled), an exasperated Ottens told his design team to create a version of their reel-to-reel tape that was small and portable, with the spools of tape contained inside a case. He wanted it to fit in a pocket and imagined it would be used by journalists and nature lovers (the latter to record birds and other outdoor sounds). Phillips introduced its new cassette system in 1963 and the immediate response was underwhelming. Before long, however, imitations of their compact cassette player began cropping up across the globe, most frequently in Japan.

Ottens then made a decision that helped boost the format. To promote standardization of the cassette, Phillips waived royalties, allowing anyone to license the design for free as long as they adhered to the company’s quality-control standards. This avoided the kind of schism that videotape would face during the VHS-Betamax war and insured that the Phillips cassette would be the dominant design. By the end of the sixties, eighty-five different manufacturers were producing cassette players, with sales of 2.5 million units. By 1983, cassettes were outselling LPs.

The ascent of the cassette caused a major freak-out among record-company executives. Nearly anyone who has ever bought vinyl will be familiar with the cassette-and-crossbones image that was for many years printed on record sleeves, accompanied by the dire warning: “Home taping is killing music.” On both sides of the Atlantic, the recording industry sought, futilely, to make the duplication of music on cassette tapes illegal. Other proposals included a compensatory tax on blank tapes.

«

Journalists and nature lovers! Inventors never know how their inventions will really be used. And strange how the same responses come to any new technology: suppress it, tax it, etc.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

The UK government intends to give energy rebates to homes near new pylons in a scheme being announced on Wednesday. CC-licensed photo by Ruben Holthuijsen on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

A selection of 9 links for you. Use them wisely. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Sam Altman’s counter-rebellion leaves OpenAI leadership hanging in the balance • WSJ

Berber Jin, Deepa Seetharaman, Tom Dotan and Keach Hagey:

»

Two days after Sam Altman was ousted from OpenAI, he was back at the company’s office, trying to negotiate his return.

The former chief executive officer entered with a guest badge on Sunday and posted on X: “first and last time i ever wear one of these.”

The leadership of the company that created the hit AI chatbot ChatGPT remained unclear Sunday, as investors and many employees pushed over the weekend to restore Altman. He has been engineering a countercoup to retake control of one of Silicon Valley’s most valuable and high-profile startups.

The abrupt shake-up at OpenAI turns on one of the oldest tales in Silicon Valley: a breakup between a founder and his board.

But in this case it was a very particular kind of founder—the face of Silicon Valley’s artificial intelligence revolution—and a very particular kind of board, which was tasked with making social good a priority over profit. The rupture threatens the future of the company and the billions of dollars investors had put into it.

Altman has also been considering starting his own venture, potentially with talent from OpenAI. He is pursuing both tracks: On Sunday morning, Chief Technology Officer and interim CEO Mira Murati sent a note to staff saying Altman would be returning to the San Francisco office later that day as discussions to reinstate him continued.

Over the weekend, Altman made clear to his allies that if he does return, he wants a new board and governance structure, people familiar with the matter said.

Two days after the board fired Altman, different explanations persisted for the initial firing. The board said Friday it pushed out the CEO after it concluded he hadn’t been candid with the company’s directors. It didn’t elaborate. 

«

At the time of compiling these links, the reason(s) for Altman’s ousting still hadn’t been made clear. Lots of people are spraying around ideas for why he was fired, hoping that their one will be true – hot take bingo – but no clear story has emerged.
unique link to this extract

Who’s on the OpenAI board — the group behind Sam Altman’s ouster • CNBC

Hayden Field:

»

On Friday, the board of OpenAI, the buzzy AI company behind viral chatbot ChatGPT, suddenly and publicly ousted its CEO Sam Altman. The announcement came one day after he appeared publicly on behalf of his company at Thursday’s APEC CEO Summit.

OpenAI’s board said it conducted “a deliberative review process” and that Altman “was not consistently candid in his communications with the board, hindering its ability to exercise its responsibilities.”

“The board no longer has confidence in his ability to continue leading OpenAI,” the board’s statement continued.

As of this week, OpenAI’s six-person board included OpenAI co-founder and President Greg Brockman, who was also chairman of the board; Ilya Sutskever, OpenAI’s chief scientist; Adam D’Angelo [Quora CEO]; Tasha McCauley [senior scientist at Rand Corporation]; Helen Toner [not an OpenAI employee]; and Altman himself. The company began publicly posting its board’s member list on its website in July, after the departures of LinkedIn founder Reid Hoffman, director of Neuralink Shivon Zilis and former Texas congressman Will Hurd.

«

Marissa Mayer – ex-Google, ex-CEO of Yahoo – tweeted that companies of OpenAI’s size would normally have 8-15 independent directors, rather than the four independent ones it does. Though of course OpenAI has grown really fast, which might have made it hard to staff up the board quickly enough.

Though board membership seems to have been something of a revolving door.
unique link to this extract

Nothing Chats has already been pulled from Google Play over privacy issues • The Verge

Wes Davis:

»

Nothing has pulled the Nothing Chats beta from the Google Play store, saying it is “delaying the launch until further notice” while it fixes “several bugs.” The app promised to let Nothing Phone 2 users text with iMessage, but it required allowing Sunbird, who provides the platform, log into users’ iCloud accounts on its own Mac Mini servers, which… isn’t great? [It offers an enormous hole for hacking – Overspill Ed]

The removal came after users widely shared a blog from Texts.com showing that messages sent with Sunbird’s system aren’t actually end-to-end encrypted — and that it’s not hard to compromise it. The app launched in beta yesterday after being announced earlier this week.

9to5Google pointed to a thread from site author Dylan Roussel, who found that part of Sunbird’s solution involves decrypting and transmitting messages using HTTP to a Firebase cloud-syncing server and storing them there in unencrypted plain text. Roussel posted that the company itself has access to messages because it logs them as errors using Sentry, a debugging service.

Sunbird claimed yesterday that HTTP is “only used as part of the one-off initial request from the app notifying back-end of the upcoming iMessage connection.”

That was in response to someone pointing to Texts.com’s blog examining the vulnerability. Texts.com wrote that “an attacker subscribed to the Firebase realtime database will always be able to access the messages before or at the moment they are read by the user.”

«

That’s so woeful. Unsurprising that Sunbird hasn’t launched publicly yet, given such truck-sized holes. Almost any of Sunbird’s team could have God Mode to read peoples’ messages.
unique link to this extract

Massive cryptomining rig discovered under Polish court’s floor, stealing power • Ars Technica

Ashley Belanger:

»

Police were called to dismantle a secret cryptomining rig winding throughout the floors and ventilation ducts of a Polish court in September, according to Polish news channel TVN24.

Several secured computers were discovered, potentially stealing thousands of Polish Zlotys worth of energy per month (the equivalent of roughly $250 per 1,000 Zlotys.) It’s currently unknown how long the rig was running because the illegal operation went undetected, partly because the computers used were connected to the Internet through their own modems rather than through the court’s network.

While no one has been charged yet with any crimes, the court seemingly has suspects. Within two weeks of finding the rig, the court terminated a contract with a company responsible for IT maintenance in the building, TVN24 reported. Before the contract ended, the company fired two employees that it said were responsible for maintenance in the parts of the building where the cryptomine was hidden.

Poland’s top law enforcement officials, the Internal Security Agency, have been called in to investigate. The Warsaw District Prosecutor’s Office has hired IT experts to help determine exactly how much electricity was stolen from Poland’s Supreme Administrative Court in Warsaw, TVN24 reported.

The Supreme Administrative Court is the last resort for sensitive business and tax disputes, but no records seem to have been compromised.

«

Quite an enterprising bit of IT outsourcing there.
unique link to this extract

US aims to triple global nuclear energy production • HuffPost UK Politics

Alexander Kaufman:

»

The United States is preparing to announce a pledge to triple the world’s production of nuclear energy by 2050, with more than 10 countries on four continents already signed on to the first major international agreement in modern history to ramp up the use of atomic power.

Signatories to the pledge, set to be unveiled at the United Nations climate summit in Dubai later this month, include many of the largest current users of nuclear energy such as the United Kingdom, France, Romania, Sweden, the United Arab Emirates, Japan and South Korea, a senior Biden administration official familiar with the efforts confirmed HuffPost. A handful of newcomers that have not yet built reactors, including Poland, Ghana and Morocco, are also said to have joined the pledge.

The plan will put pressure on the World Bank to end its long-standing ban on financing nuclear-energy projects, which the American Nuclear Society, a nonprofit of academics and industry professionals who advocate for atomic energy in the public interest, said was crucial to any buildout.

“Tripling the world’s nuclear energy supplies by 2050 is the catalyst required to halt rising temperatures and achieve a sustainable future,” the ANS said in a statement to HuffPost. “A large-scale build-out of new nuclear energy can only happen with the crafting of nuclear-inclusive lending policies by financial institutions like the World Bank.”

«

I had no idea that the World Bank had such a ban in place. Utterly bonkers.
unique link to this extract

Autumn Statement: Homes close to new pylons to get £1,000 off bills • BBC News

»

Households living close to new pylons and electricity substations could receive up to £1,000 a year off energy bills for a decade under new plans.

It is hoped the plan would convince people to support upgrades in their area, which are needed in part for new electric vehicle charging points.

Chancellor Jeremy Hunt is expected to announce the policy in the Autumn Statement on Wednesday.
It is unclear at this stage how many households will get the full discount.

Mr Hunt and Prime Minister Rishi Sunak are currently finalising the content of the statement, which will set out the priorities for government spending in the final year before a general election has to be held.

It is known that they are considering announcing some tax cuts, and changes to income tax, national insurance, inheritance tax and business taxes are all being discussed.

But the Treasury has indicated the pounds-for-pylons plan will definitely form part of the chancellor’s statement.

«

This might be useful, inasmuch as yes, we do need more pylons. But also what about discounts for being near new onshore wind turbines? Or new nuclear power stations? There’s such a paucity of imagination.
unique link to this extract

MPs want UK national security law used to vet Barclay family’s Telegraph offer • The Guardian

Julia Kollewe:

»

MPs, including Edward Leigh, John Hayes and the life peer Margaret Eaton, have written to the deputy prime minister, Oliver Dowden, the business secretary, Kemi Badenoch, and the culture secretary, Lucy Frazer, questioning the use of overseas sovereign wealth to buy Telegraph Media Group, the Financial Times reported.

The Barclays had owned the group, which includes the Daily and Sunday Telegraph as well as the Spectator, since 2004 but Lloyds Banking Group took control of it in June after the family failed to reach an agreement over more than £1bn in unpaid debt. It has since been put up for sale by the bank in an auction run by Goldman Sachs.

Last month, the Barclay family tabled an offer valuing the newspaper group at £1bn in an attempt to deter rival bidders from challenging them before the auction. The family has secured financing from investors based in Abu Dhabi in the United Arab Emirates, after talks that began in August.

The MPs said in the letter that they were concerned that investment vehicles with links to the UAE royal family “may soon gain control of or material influence over two of the most important media publications in Great Britain, the Telegraph and the Spectator”.

They argued that there “is a strong case for close scrutiny by the government under both the Enterprise Act 2002 and the National Security and Investment Act 2021”, especially if the offer involved taking the publications as security for the loan, “an amount which, by any sensible measure, the revenue of the publications will not be able to support”.

«

So the MPs are saying they don’t think the titles are worth anything like that much, and that the loans will fall into default. Hard to argue: the Telegraph titles have been valued around £500m-£700m.
unique link to this extract

Ad execs urge Twitter CEO to resign after Musk endorses antisemitic post • Forbes

John Paczkowski:

»

Forbes has confirmed that Yaccarino has been contacted by a groundswell of leading advertising executives who questioned why she is risking her reputation to shield Musk’s behavior—and suggested that she could make a statement about racism and antisemitism by stepping down. She has so far resisted their entreaties, sources said.

Last week, Musk endorsed an explicitly antisemitic conspiracy theory, and a report from watchdog Media Matters found that ads from major companies including IBM and Amazon had been placed next to content promoting Nazis and white nationalism, prompting advertisers including Apple, Disney and IBM to pull ads from the platform. Even the White House has condemned Musk’s antisemitic and racist statement, in which Musk agreed with an X user who espoused a conspiracy theory that “Jewish communities have been pushing the exact kind of dialectical hatred against whites that they claim to want people to stop using against them.”

On November 16, Yaccarino responded to the firestorm in a post on X: “X’s point of view has always been very clear that discrimination by everyone should STOP across the board — I think that’s something we can and should all agree on. When it comes to this platform — X has also been extremely clear about our efforts to combat antisemitism and discrimination. There’s no place for it anywhere in the world — it’s ugly and wrong. Full stop.” Yaccarino did not immediately respond to a comment request made through X’s press team.

The personal outreach to Yaccarino by leading advertising executives comes as X, previously known as Twitter, struggles to right itself under its mercurial owner and to battle the advertiser-unfriendly content his behavior has emboldened.

«

You have to wonder what she thinks she’s getting out of it. Every blowup like this shows how powerless she is to control Musk, and how pointless her position is.
unique link to this extract

Ads watchdog files FTC complaint against X, formerly Twitter, over unlabeled ads • TechCrunch

Sarah Perez:

»

X, formerly Twitter, was caught running unlabeled ads on its platform in September. Now that issue, which has been ongoing, has been brought to the FTC’s attention. An independent nonprofit Check My Ads has filed a formal complaint with the U.S. Federal Trade Commission urging an investigation over the advertising practices at X, including the lack of disclosure about which posts are ads, broken links that explain why ads are targeted and more.

The complaint cites X’s lack of disclosure around ads, saying it misleads consumers that the content and the information they’re consuming on the platform is not paid for.

“This misrepresentation tricks users into trusting content as organic and exacerbates the opportunity for scams to occur,” the complaint states. “Furthermore, by failing to adequately disclose advertisements, X Corp. misrepresents the methods employed to target users or facilitate third-party ad targeting.”

It also points out that X’s promotional materials for advertisers indicate that advertisements are distinguished from non-paid, organic content with a “Promoted” label, but no such label appears for consumers. As Mashable earlier reported, X appeared to be switching between the “Promoted” and “Ad” labeling format for some time. Most of the ads on X are now simply labeled “Ad” but some are surfacing in users’ feeds without any ad label attached at all.

«

When things go bad, they go really bad.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified

Analysis suggests it was a tweet, not TikTok, which made Osama bin Laden’s manifesto go viral. CC-licensed photo by justgrimes on Flickr.

You can sign up to receive each day’s Start Up post by email. You’ll need to click a confirmation link, so no spam.

It’s Friday, so there’s another post due at the Social Warming Substack at about 0845 UK time. It’s about David Cameron, and the past following you around.

A selection of 9 links for you. Use them wisely. I’m @charlesarthur on Twitter. On Threads: charles_arthur. On Mastodon: https://newsie.social/@charlesarthur. Observations and links welcome.

Apple announces RCS support for iMessage • Ars Technica

Ron Amadeo:

»

Apple shocked the mobile world on Thursday by saying it will adopt the RCS messaging standard. When iMessage users are talking to people off the service, iMessage will soon be able to fall back to the RCS carrier messaging standard instead of SMS, which comes with the advantages of read receipts, higher-quality media sending, and typing indicators. Your chats with your green bubble friends will be slightly less awful.

Apple sent several media outlets a statement:

»

Later next year, we will be adding support for RCS Universal Profile, the standard as currently published by the GSM Association. We believe RCS Universal Profile will offer a better interoperability experience when compared to SMS or MMS. This will work alongside iMessage, which will continue to be the best and most secure messaging experience for Apple users.

«

iMessage is currently besieged on all sides by various parties. Google has been waging a “get the message” campaign against Apple for the past year or two, imploring the company to adopt RCS.

Last year, Apple CEO Tim Cook was asked on stage if the company would make messaging with Android better, and he responded, “I don’t hear our users asking that we put a lot of energy in on that at this point” and told the audience member to “just buy your mom an iPhone” if he wanted easier communication with his mother. Regulators in the European Union have yet to decide the fate of iMessage, but if it meets the qualifications for being a big tech “Gatekeeper,” the iMessage protocol will be forced to open up in the EU. [Thursday was the last day before the EU might have forced Apple to offer iMessage interoperability – Overspill Ed]

The Wall Street Journal ran an article last year subtitled “Teens Dread the Green Text Bubble,” detailing the bullying that Android users were subject to due to SMS fallback dragging down the capabilities of iMessage group chats (87% of US teenagers have iPhones).

On the Android side of things, companies have been desperate to work better with iMessage, with Google hacking together an emoji response solution for Google Messages and Android manufacturer Nothing planning a wild “hack into iMessage” scheme to run messages through Mac computers hosted in a data center.

«

RCS was devised in 2008, and Google started pushing it harder in 2017. But to actually bang heads together, you need a trade bloc, just as with GSM decades ago.
unique link to this extract

Apple’s in-house 5G modem work faces further delays • MacRumors

Juli Clover:

»

Apple is continuing to run into troubles in its attempt to develop a 5G modem to replace Qualcomm’s 5G modems in the iPhone and other products, reports Bloomberg’s Mark Gurman.

Apple in 2019 acquired the majority of Intel’s smartphone business and started in on a serious effort to develop its own modem hardware, but the project has suffered multiple setbacks. Apple is still “years away” from creating a chip that is able to perform as well as or better than chips from rival Qualcomm.

The Cupertino company initially wanted to have an in-house modem chip ready to go by 2024, a goal that could not be met, and now Gurman says that Apple is also going to miss an extended spring 2025 launch timeline. As of now, the modem chip launch has been postponed until the end of 2025 or early 2026, and Apple is still planning to introduce the technology in a version of the low-cost iPhone SE.

Development on a modem chip is said to be in the early stages, and it “may lag behind the competition by years.” One version in development does not support faster mmWave technology, and Apple has also run into issues with the Intel code that it has been working with. Rewrites have been required, and adding new features has been causing existing features to break, plus Apple has to be careful not to infringe on Qualcomm patents while developing the chip.

…[Apple and Qualcomm] signed a new contract [for Apple to use Qualcomm’s modems], which was extended in September 2023. The latest deal with Qualcomm covers smartphone launches in 2024, 2025, and 2026, and will last through Apple’s delayed modem chip development.

«

Zeno’s modem? It seems like it’s always two, maybe three years away.
unique link to this extract

Russian troops deployed on a motorbike. A drone chased them down • Forbes

David Axe:

»

On Oct. 19, Ukrainian marines in small boats motored across the Dnipro River in southern Ukraine’s Kherson Oblast, landed in the Russian-occupied settlement of Krynky and, in a series of infantry actions, seized a bridgehead across the river.

Provided Russian motor-rifle regiments don’t soon push the marines back into the river, the Krynky lodgment could serve as a base for a wider Ukrainian offensive in Kherson.

In the meantime, it’s an object-lesson in local air-superiority. A lesson a pair of motorbike-riding Russian air-defense troops learned the hard way, as an explosives-laden Ukrainian first-person-view drone chased them down and killed them in dramatic fashion in Krynky recently. Warning: the video of the strike is extremely graphic.

The Krynky river-crossing was the culmination of a long preparatory campaign by Ukrainian pilots, gunners, drone-operators and electronic-warfare specialists who struck Russian supply lines and air-defenses, suppressed Russian artillery, harried Russian strongpoints and—perhaps most critically—jammed Russian drones and struck electronic-warfare systems in order to keep the Russians from jamming Ukrainian drones.

And now the air over Krynky belongs to Ukrainian drone-operators and daring Ukrainian army helicopter pilots flying low-level rocket-attack sorties. Russian troops cannot venture out into the open in and around Krynky without drawing the attention of Ukrainian aircraft.

As early as June, there were reports the Ukrainians were positioning powerful radio-jammers on the Dnipro’s right bank in order to create a 12-mile-deep zone where Russia’s explosive FPV drones cannot reliably operate, but Ukrainian drones can operate.

«

Black Mirror’s “Hated in the Nation“, written by Charlie Brooker: fiction in 2016, a grim reality seven years later.
unique link to this extract

Sphere and Loathing in Las Vegas • The Atlantic

Charlie Warzel:

»

It is the architectural embodiment of ridiculousness, a monument to spectacle and to the exceedingly human condition of erecting bewildering edifices simply because we can. It cost $2.3bn; it’s blanketed in 580,000 square feet of LED lights; it can transform its 366-foot-tall exterior into a gargantuan emoji that astronauts can supposedly see from space. This is no half dome and certainly not a rotunda. This is Sphere.

When I approached the Sphere on the ground, around dusk, the building awoke from its screen saver (an unpleasant advertisement for a Spider-Man video game) and began to emit a strange burbling noise. A semi-realistic animation of a womb-bound fetus appeared and spoke the words “This is not a rehearsal” before bursting into flames, flickering violently, and shape-shifting into the following series of images: a blinking eyeball, a thunderstorm, the ocean, some plants, the moon, more flames, all to the pounding drums and metallic guitar clanking of U2’s “Zoo Station.” Even in the context of the pulsing neon goat rodeo of the Vegas Strip, this was a sensory assault.

The kaleidoscopic display made a certain kind of sense, because the Sphere is itself many different things. It’s an arena, conceived by the Madison Square Garden Company in 2018, and home to an ongoing U2 residency. It’s a movie theater, too, like 42 and a half IMAX screens bolted together. (The filmmaker Darren Aronofsky has been screening Postcard From Earth, a documentary he made specifically for this curved megatron.) The Sphere is a new form of architecture, a billboard, a digital canvas for art, and it is a weenie—which, my colleague Ian Bogost informed me, is a term invented by Walt Disney to describe landmarks inside his theme parks that help orient visitors. Las Vegas is a city of weenies, and the Sphere is its most glamorous.

«

A great piece of writing by Warzel, but that headline has subeditors all over the internet grinding their teeth in envy at not having written it.
unique link to this extract

AI chatbots just showed scientists how to make social media less toxic • Business Insider

Adam Rogers:

»

On a simulated day in July of a 2020 that didn’t happen, 500 chatbots read the news — real news, our news, from the real July 1, 2020. ABC News reported that Alabama students were throwing “COVID parties.” On CNN, President Donald Trump called Black Lives Matter a “symbol of hate.” The New York Times had a story about the baseball season being canceled because of the pandemic.

Then the 500 robots logged into something very much (but not totally) like Twitter, and discussed what they had read. Meanwhile, in our world, the not-simulated world, a bunch of scientists were watching.

The scientists had used ChatGPT 3.5 to build the bots for a very specific purpose: to study how to create a better social network — a less polarized, less caustic bath of assholery than our current platforms. They had created a model of a social network in a lab — a Twitter in a bottle, as it were — in the hopes of learning how to create a better Twitter in the real world. “Is there a way to promote interaction across the partisan divide without driving toxicity and incivility?” wondered Petter Törnberg, the computer scientist who led the experiment.

It’s difficult to model something like Twitter — or to do any kind of science, really — using actual humans. People are hard to wrangle, and the setup costs for human experimentation are considerable. AI bots, on the other hand, will do whatever you tell them to, practically for free. And their whole deal is that they are designed to act like people. So researchers are starting to use chatbots as fake people from whom they can extract data about real people.

“If you want to model public discourse or interaction, you need more sophisticated models of human behavior,” says Törnberg, an assistant professor at the Institute for Logic, Language, and Computation at the University of Amsterdam. “And then large language models come along, and they’re precisely that — a model of a person having a conversation.” By replacing people as the subjects in scientific experiments, AI could conceivably turbocharge our understanding of human behavior in a wide range of fields, from public health and epidemiology to economics and sociology. Artificial intelligence, it turns out, might offer us real intelligence about ourselves.

«

They used three models: “Echo chamber” full of people who agree with you, “Discover” (sort of “For You”) offering views from all over, and “Bridge”, showing what was most popular with political opposites. Have a guess at which caused the least rancour, and then read it.
unique link to this extract

Trade with Europe ‘harder than ever’ for UK businesses • The London Economic

Jack Peat:

»

A comprehensive new survey of UK businesses has exposed the reality of trade with Europe post-Brexit, pointing to ongoing damage to the UK economy caused by the split.

A whopping 94% of respondents to the European Movement poll said leaving the single market and customs union has had a negative effect, while hundreds reported having to reduce their workforce hours, make staff redundant, or even close entirely.

Companies across sectors including engineering, agriculture, hospitality and finance reported they had lost business in the EU, and been made uncompetitive by new red-tape.

More than half of respondents said new red tape had made trading with the EU increasingly difficult, calling it ‘the single biggest obstacle’ to doing business with our largest trading partner.

A further 40% highlighted problems with finding staff since the loss of Freedom of Movement.

Sir Nick Harvey, CEO of European Movement UK, said: “This research shows just how difficult trading with the EU has become for British businesses. Many we have talked to have either cut down their exports into the bloc, or stopped them entirely, citing new costs, increased red tape, and diminishing confidence from EU businesses in UK suppliers. The voices of our small and medium businesses are not being heard, and times are harder than ever.

“Their stories are the ugly truth of trading for UK business after exiting the EU.”

«

Predictable. In case you haven’t heard of The London Economic: here’s the About page.
unique link to this extract

Users can’t speak to viral AI girlfriend CarynAI because CEO is in jail for arson • 404 Media

Emanuel Maiberg and Jason Koebler:

»

People who paid to speak to an AI girlfriend modelled after real life 23-year-old influencer Caryn Marjorie are distraught because the service they paid for, Forever Companions, no longer works. It appears that the service stopped working shortly after Forever Companion CEO and founder John Meyer was arrested for trying to set his own apartment on fire. 

…“I terminated my relationship with Forever Voices due to unforeseen circumstances,” Marjorie told 404 Media in an email. “I wish the best for John Meyer and his family as he recovers from his mental health crisis. We didn’t see this coming but I vow to push CarynAI forward for my fans and supporters.”

…CarynAI became a viral sensation in May, getting coverage at NBC News, Fortune, Washington Post, and many other publications. While the service was not explicitly promoted for providing adult content, that is what it turned to immediately after users get their hands on it.

«

But of course it did.
unique link to this extract

TikTok is removing videos praising Osama bin Laden letter • Semafor

J.D. Capelouto and Louise Matsakis:

»

TikTok says it’s “aggressively removing” videos promoting Osama bin Laden’s 2002 “Letter to America,” which explained why he orchestrated the terrorist attacks on Sept. 11, 2001. The platform has also blocked the hashtag #LettertoAmerica, meaning users won’t be able to search for it, a TikTok spokesperson told Semafor.

Several videos from creators encouraging others to read the letter or sympathizing with bin Laden’s views on Israel and the U.S. racked up tens of thousands of views on TikTok and other platforms in recent days. Google Trends data indicates that searches for the document began spiking around a week ago.

Critics argued the videos showed that TikTok was spreading harmful information to young people, who make up a large bulk of its user base. But the platform said in a statement on X that the number of videos about the letter “is small and reports of it trending on our platform are inaccurate.” The statement added: “This is not unique to TikTok and has appeared across multiple platforms and the media.”

In its statement, TikTok said that content “promoting this letter clearly violates our rules on supporting any form of terrorism,” adding that it is “investigating how it got onto our platform.” TikTok has been at the center of the conversation about how the Israel-Hamas war is playing out on social media, in part because of a narrative that the app, which is Chinese-owned, leans pro-Palestine.

…Many TikTok users originally read the letter on the website of The Guardian, where it amassed over 100,000 views in recent days before the newspaper took it down, according to a person familiar with the matter. Another person at The Guardian told Semafor that almost all of the traffic came from people searching for the letter on Google, starting on Nov. 9.

The Guardian said it deleted bin Laden’s letter from its website because it was being shared on social media without its original context.

«

Lot of side eye at TikTok’s apparent boosting of this, but analysis by Ryan Broderick suggests that what made it “go viral” was a tweet.
unique link to this extract

Apple should share its knowledge of Indian politicians’ iPhone hacks • Rest of World

Barkha Dutt:

»

India’s opposition has accused the government of spying on them after multiple iPhone users in the country received an alert from Apple. “State-sponsored attackers may be targeting your iPhone,” the automated text message read. So far, all the members of Parliament who have come forward about receiving the alert are those who oppose the ruling Bharatiya Janata Party.

An inevitable political row has followed.  

But amid the outrage, Apple’s muted public response has been perplexing, obfuscatory, and contradictory. So far, the iPhone manufacturer has not released a formal public statement. Attributions have been made to sources, government officials, or what Apple has purportedly said when contacted for a response. The absence of any clear or constituent articulation from the American technology giant has left the space wide open for random mudslinging and unverifiable claims and counterclaims.

The Narendra Modi government, while announcing an inquiry, has also described the protesting political figures to be “compulsive critics.” Officials say the alert is “vague,” generic, and no more than an automated advisory sent out in 150 countries.

“If it’s an algorithm tripping up, how can you explain why only one side of the political aisle has been warned?” argued Priyanka Chaturvedi, an opposition leader who received Apple’s alert, in an interview with me.

…In 2021, there was a national furore when a global investigative project reported that Pegasus spyware, developed by Israel’s NSO Group, had been used to target the devices of at least 50,000 individuals globally, including serving ministers, journalists, and opposition members in India. Two years later, a panel of experts failed to reach any clarity. The inquiry panel informed the Indian Supreme Court that the government had failed to cooperate. Malware was found on some devices but could not conclusively be linked to Pegasus. The government refused to confirm or deny whether it owned or used Pegasus.

«

The complaint in this article is that Apple isn’t telling the targeted people who is targeting them, but it seems very likely that Apple doesn’t know; it can just detect something from the logfiles of the devices that say things are awry. It’s always been difficult to know who’s controlling Pegasus; if this is the same or a different piece of spyware, you’d expect the same.
unique link to this extract

Errata, corrigenda and ai no corrida: none notified