November 24, 2024

Hello, fellow humans! You are reading our limited series of Saturday Daily Briefs. Although focused on AI, it is compiled, written and edited by real people.

Have some questions about AI that you’d like answered? Or just some AI hallucinations you’d like to share? Email us anytime. Enjoy it!

Correction: Friday’s Daily Brief incorrectly referred to Viktor Orbán as the prime minister of Turkey. He is the prime minister of Hungary.


Here’s what you need to know

Intel has a new AI chip. The company’s Gaudi3 is due out next year compete with competing technology made by Nvidia and AMD.

OpenAI’s nonprofit earned just $45,000 last year. With private investors appreciate the company at $86 billion, its finances remain a black box.

Meanwhile, one of OpenAI’s rivals in Paris raised €385 million ($415 million) in its latest funding round. Mistral AI’s valuation, however, is $2 billion– a far cry from the ChatGPT creator’s.

The parent company of Business Insider and Politico has signed a content deal with OpenAI. The agreement will allow ChatGPT to use articles from Axel Springer’s publications to answer user commands and provide links to those stories.


Antitrust in an AI World

The UK’s antitrust agency, the Competition and Markets Authority, is gathering information about Microsoft and OpenAI to decide whether their partnership threatens competition in the UK, which Google’s AI subsidiary DeepMind call home

The fast-moving generative AI industry is increasingly attracting the attention of regulators worldwide. At the moment, the CMA is only seeking comments from the firms, but that move could lead to a formal antitrust investigation by the UK agency.

Greater antitrust scrutiny makes it harder for AI-focused companies to join forces. Amazon, Google and Meta have responded by finding ways to work with startups rather than buying them outright, Brendan Burke, an analyst at PitchBook, previously told Quartz. But after OpenAI’s recent turmoil, a spotlight was placed on his ties with Microsoft it’s hard to dim.


Google is doubling down on live action AI

When Google has dropped its new generative AI model Gemini in a pre-recorded video demo last week, it highlighted the differentiating elements of the ChatGPT competitor, such as its ability to speak out loud. But there seemed to be a gap between what was shown and the big language model’s true capabilities.

Sure enough, Google admitted the video was edited. The YouTube description of the demo said “Latency has been reduced and Gemini outputs have been shortened for brevity,” making the AI ​​system seem more responsive than it is.

The staged aspects of the demo were called out by websites such as Bloomberg and TechCrunch, not a good look for the ChatGPT competitor racing to catch up with OpenAI. Google should have taken notice and returned this week with live demos of its Gemini Pro and other AI tools. The change in approach underscores the need for Google to build confidence in its generative AI capabilities—but investors will take note?


Quotes: Putin, meet Putin

“Vladimir Vladimirovich, hello, I am a student at the St. Petersburg State University. I want to ask, is it true that you have many doubles?”— an AI-generated version of Russian President Vladimir Putin asked the real Vladimir Putin during an annual news conference on Thursday.

The real Putin hesitated briefly, then said: “I see you may look like me and speak with my voice. But I thought about it and decided that only one person should be like me and speak with my voice, and that would be me.”


Other great AI readings

🙏 The Pope, once a victim of AI-generated imagery, calls for a treaty to regulate it

🫣 2023 was the year we played with AI, and we weren’t sure what to do with it

💻 Oracle literally can’t build enough cloud computing for Elon Musk’s xAI

🇪🇺 Europe has agreed on world-leading AI rules. How do they work?

🇲🇾 Nvidia’s CEO thinks Malaysia can be an AI manufacturing hub

☁️ AWS Chief Adam Selipsky talks about AI, Anthropic and cloud cost savings


Ask an AI

Earlier this week we told you how Tesla had to recall nearly 2 million vehicles in North America to fix its Autopilot feature. The company is adding more features to ensure drivers are paying attention, but safety experts say it’s not enough. The real problem, they insist, is not drivers but the technology itself, which has trouble spotting obstacles and shouldn’t be allowed on the road.

We asked the Grok AI (only available with an X Premium+ subscription), another Elon Musk product, to weigh in on the question of whether self-driving cars are safe. It said: “I believe that self-driving car technology has come a long way and is generally safe. However, like any technology, it is not perfect, and there have been cases where accidents have occurred. As a humorous AI, I would say that self-driving cars are like teenagers learning to drive – they’re pretty good most of the time, but every now and then they might make a questionable decision.In all seriousness though, it’s imperative for companies to continue to develop the technology improve and address safety issues to ensure a smooth and safe ride for everyone on the road.”

Grok self-identifies as humorous, it pulls its information from tweets, and it’s still in its infancy, so it can’t really be considered the most useful or reliable AI out there. But it’s hard not to read the above quote and raise an eyebrow or two.

When we asked Grok how an autopilot function would keep a driver and those around them safe, it did have this helpful tip: “While the autopilot function can help with steering, it’s essential to always maintain control of the vehicle. Think of it like holding hands with a friend—you’re there to support each other, but you’re still in control of your own actions.” Ouch!


Did you know we also have two premium weekend emails? One gives you analysis of the week’s news, and one provides the best reads from Quartz and elsewhere to start your week off right. Become a member or give membership as a gift!

Our best wishes for a very human day. Send any news, comments, management tips and Putin calendars to praat@qz.com. Reader support makes Quartz available to everyone—become a member. Today’s AI in Focus Daily Brief is brought to you by Morgan Haefner and Susan Howson.

l
m
p
e
d
p
b
T
F
T
G
M
t
F
T
P
U
C
A
H
T
p
Z
m
t

Leave a Reply

Your email address will not be published. Required fields are marked *