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.
«
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
| • Why do social networks drive us a little mad? • Why does angry content seem to dominate what we see? • How much of a role do algorithms play in affecting what we see and do online? • What can we do about it? • Did Facebook have any inkling of what was coming in Myanmar in 2016? Read Social Warming, my latest book, and find answers – and more. |
Errata, corrigenda and ai no corrida: none notified
The Overspill: when there's more that I want to say 