Based on the complaints I’m seeing about the new rate limits, I think the GitHub copilot subreddit may actually go to war tomorrow once this gets announced

Private equity courts OpenAI and Anthropic The start-ups are in talks with private equity firms over joint ventures intended to help deploy AI in businesses

The final boss has emerged
www.ft.com/content/693d...

I want to be very clear about something: for OpenAI to be able to pay the deals it has signed it will have to be ten to fifteen times its current revenue and have raised at least another $150 billion. If it fails, Oracle will run out of money, and not pay its debts.

Google Starts Scanning All Your Photos As New Update Goes Live Google wants its AI to see all the photos of "you and your loved ones." Billions of users must now decide.

“Take a moment to think before you dive in. That’s the best advice for Google Photos users, as the company confirms its latest update can scan all your photos to “use actual images of you and your loved ones” in AI image generation.”

www.forbes.com/sites/zakdof...

I'm not joking when I say mRNA technology is more important than "AI" and it's a tragedy we're throwing billions into one while our government is aggressively defunding the other.

"Synthetic Propaganda - Tracing an AI-Driven Political Operation" with Effie Webb | Podcast Episode on RSS.com This week we spoke with The Bureau of Investigative Journalism's AI reporter, Effie Webb about the use of AI in the political sphere and what researchers/journalists can effectively report on AI misus...

AI-generated content has entered the political sphere. Bellingcat speaks with @tbij.bsky.social reporter @efwebb.bsky.social on a possible first-of-its-kind case—and what it means for tracking AI misuse in politics. Listen by searching 'Stage Talks with Bellingcat': rss.com/podcasts/bel...

Opening text of a thread by Palantir from X Because we get asked a lot. The Technological Republic, in brief. 1. Silicon Valley owes a moral debt to the country that made its rise possible. The engineering elite of Silicon Valley has an affirmative obligation to participate in the defense of the nation. 2. We must rebel against the tyranny of the apps. Is the iPhone our greatest creative if not crowning achievement as a civilization? The object has changed our lives, but it may also now be limiting and constraining our sense of the possible. 3. Free email is not enough. The decadence of a culture or civilization, and indeed its ruling class, will be forgiven only if that culture is capable of delivering economic growth and security for the public. 4. The limits of soft power, of soaring rhetoric alone, have been exposed. The ability of free and democratic societies to prevail requires something more than moral appeal. It requires hard power, and hard power in this century will be built on software.

Palantir put out a 22-point summary of their CEO's book The Technological Republic. It's pitched as a defence of the West, but if you read it through the VDA framework, verification, deliberation, accountability, what it's actually doing looks rather different.
twitter-thread.com/t/2045574398...

That Palantir would do this is both shocking—not because this is some weird heel turn, but because it is a fully mask-off moment for tech bro fascisti—and also the least surprising thing from a company that has always been creepy as fuck.

Communication Bias in Large Language Models: A Regulatory Perspective Large language models (LLMs) are increasingly central to many applications, raising concerns about bias, fairness, and regulatory compliance. This paper reviews risks of biased outputs and their socie...

There is a new study about the bias in Large Language Models, which is especially concerning when it comes to political topics and public opinion.
arxiv.org/abs/2509.21075

ChatGPT & Co.: Wie LLMs politische Perspektiven verzerren - Interview mit Stefan Schmid ChatGPT & Co.: Eine neue Studie beleuchtet, wie Large Language Modelle politische Debatten verzerren. Interview mit Stefan Schmid, TU Berlin.

💬 Wie verzerren LLMs politische Perspektiven? Eine Studie von Stefan Schmid und Adrian Kuenzler legt dar, dass diese Systeme keineswegs neutral operieren. Die Ergebnisse der Studie ordnet Stefan Schmid in der Deutschlandfunk-Radiosendung „@mediasres“ ein
🎧 Jetzt reinhören:

Spaceman world, caveman problems

Mehr Paper, sinkende Qualität: Der Umgang der Wissenschaft mit KI-Tools ist verantwortungslos Der Einsatz von generativer KI in der Forschung höhlt zentrale Prinzipien der Wissenschaft aus, kommentiert Jens Foell.

"Viele Chatbots machen ihre Arbeit oft schlecht und verstecken ihre grundlegende Unfähigkeit hinter einer Fassade aus Selbstbewusstsein und vorgegaukelter Kompetenz." Immer mehr Einreichungen und sinkende Qualität von Publikationen. www.spektrum.de/kolumne/der-...

stargate is dead - or more operatively never actually existed. Norway was never happening. Next up on the deathwatch is Stargate Argentina, which was only ever a letter of intent.

Also fair to ask whether OpenAI ever takes Oracle's data centers.

www.wheresyoured.at/hatersguide-...

Musk’s Grok AI chatbot is still making sexual deepfakes, despite X’s promise to stop it An NBC News review found dozens of AI-generated sexualized images of real women posted to X over the past month.

We dove into Grok's continued creation of deepfakes, and found that some users have found new methods to bypass Grok's guardrails, allowing them to generate sexual AI images of celebrities and real people.

from @davidingram.bsky.social

www.nbcnews.com/tech/tech-ne...

I love those examples of implementation of large language models, because they show everyone how useless these models are.

doordash grandma DoorDash does not have a specific policy for seniors or helping grandparents, as the provided articles do not mention DoorDash's policies or services for seniors. If you have a follow-up question, feel free to let me know. how the fuck do I just search WaPo articles? To search Washington Post articles, you can use the "Ask The Post Al" tool, which is a generative Al tool that provides summary answers and curated results directly to users. If you have a follow-up question, feel free to let me know. I asked. Show me article about "doordash grandma" There is no information about DoorDash and grandma in the provided articles. If you have a follow-up question, feel free to let me know.

WaPo website replaced search with AI and it's going great

Ein Stimmzettel für den Olympia-Entscheid in Köln

Olympia ja oder nein? Auch ich darf darüber abstimmen, ob Köln sich für die Ausrichtung von Sommerspielen bewerben soll. Von Freunden wurde ich öfter gefragt, was von einer Bewerbung zu halten ist. Ich habe dann immer dagelegt, warum ich mit NEIN stimme werde. Das mache ich jetzt auch mal hier. ⬇️

Interesting paper on AI assisted job interviewing. Study finds that "asnchronous interviews" reduce application continuation by 53%. Most qualified are lost, stronger effects for women. Cool, cool, cool
papers.ssrn.com/sol3/papers....

Here's a rundown of what happened when Grammarly used our staff's likenesses for their janky AI "experts" feature

Sutskever would later sit down with New York Times reporter Cade Metz for his book Genius Makers, which recounts a narrative history of AI development, and say without a hint of satire, "I think that it's fairly likely that it will not take too long of a time for the entire surface of the Earth to become covered with data centers and power stations." There would be "a tsunami of computing. almost likea natural phenomenon." AGI-and thus the data centers needed to support them-would be "too useful not to exist”

I see a lot of techies perplexed about the venom the rest of society has about AI. here’s just one sample of why so many people reflexively loathe AI

Paper Finds That Leading AI Chatbots Like ChatGPT and Claude Remain Incredibly Sycophantic, Resulting in Twisted Effects on Users A study found that sycophancy is pervasive among chatbots, and that bots are more likely than human peers to affirm a person's bad behavior.

“Just one interaction with a flattering chatbot was likely to ‘distort’ a human user’s ‘judgement’ and ‘erode prosocial motivations,’ an outcome that persisted regardless of a person’s demographics and previous grasp on the tech…”

Almost Half of US Data Centers That Were Supposed to Open This Year Slated to Be Canceled or Delayed The vast majority of data centers scheduled for completion over the next few years have yet to even break ground.

It's indeed possible to beat bad things backed by big money

I mean, how do you explain this as somebody buying copilot? “Oh just ignore that”?

Title: Hunting for Easter eggs with Werner Herzog Panel one: Werner goes out looking for eggs saying “I despise this idiotic sanitized ritual, and yet I am unwilling to return home eggless” Panel two: Werner stands before an egg on the ground “The joy of discovery rings hollow against the monumental indifference of the universe” Panel three: Werner carries an egg “what, other than regret, can hatch from this empty chocolate vessel”

Happy Easter!

A full disc image of Earth, as seen from the Orion Crew Module. The planet is a pale blue, swirling with white clouds and glowing slightly lighter blue in place from reflected light. At lower left, a large brown landmass is Africa, with Spain and Portugal with twinkling lights where the planet curves. At top right, auroras glow in a thin green glow, just barely separated from the planet's surface. Earth is set against the black of space (pic: NASA/R.Wiseman)

More context on this #Artemis II image:

* This is the night side, lit by moonlight. You can see city lights in Spain & Portugal, & a sliver of day at lower right

* The Sun is entirely behind Earth, which makes it a kind of solar eclipse, but w/ Earth doing the eclipsing instead of the Moon:
☀️🌍🚀🌕

Waiting for the AI bros to come in and well-ahktually this one.

It's bad to burn lots of carbon for absolutely no benefit, period.

So fucking funny to sell this to big businesses and world governments

This analyst saying this says that Microsoft has to “fix copilot” as if the problem is something that simply requires more compute, versus an inherent issue with LLMs. He also buys into the (completely fake) “ai is eating software” story. I could do this job! It’s easy!

That is why I have deposited peanuts in all my bags and backpacks. The looks of disappointed crows are just too much to deal with.

Jon Hartley ® @Jon_Hartley_ X.com * Another update to our Generative AI US adoption time series results from our paper "The Labor Market Effects of Generative Artificial Intelligence": we find LLM adoption at work in the US fell over the past quarter (while still up substantially from a couple years ago). 100% Fraction of U.S. Labor Force Using Generative AI At Work 90% 80% 70% 60% (%) 50% 40% 30% 20% 10% 0% May-22 Dec-22 -Pew Survey (ChatGPT use) -I-Bick, Blandin, Deming Gen Al Survey -Hartley, Jolevski, Melo, Moore Gen Al Survey Public Release of ChatGPT (First Public Large Language Model) Jun-23 Jan-24 Jul-24 Feb-25 Aug-25 Mar-26 Oct-26

I like how every study that tries to prove AI is being adopted at scale is like “jobs that AI might be able to do a small amount of are sort of affected” and every other study on AI use is “adoption is low” and “it doesn’t really work reliably or in a way with measurable outcomes”