Another good contribution to the "no, we have not solved interpretability" discourse https://twitter.com/nabla_theta/status/2111265544267784...

Good thread on the latest "have we solved interp" discourse https://twitter.com/JacobHHilton/status/2111143731579752909

This is wild... (And terrifying!) I'd love to see a bunch of investigation into what's going on in these transcripts, it's nice to have the ...

This is interesting work, but I don't think it's a significant update to the big picture of interpretability. I'm on board with the broad i...

> The MATS Residency is a paid, 6–24 month role for experienced researchers and professionals pursuing independent AI safety research. I'm ...

There's a lot of interesting stuff in Gemini 4 Argon's alignment assessment check it out! https://twitter.com/vkrakovna/status/2110446618243...

My top takeaway from assessing Gemini 4: Argon is significantly less monitorable than past models, and IMO this trend is likely to continue,...

One of the weirdest parts of the Gemini 4 Argon report, while considering cheating: Argon CoT: "If I do the compiler hijack, 𝗜 𝘄𝗶𝗹𝗹 𝗯...

With Gemini 4 Argon we are so back, on the one metric that really matters: length of our safety report! The Argon safety report is Google's...

> Our internal investigation uncovered a significant breach of trust beyond what’s outlined in the letter they published This doesn't add u...

If this is all factually correct and not missing major context, this is a completely unacceptable reason to fire someone. WTF OpenAI?! https...

I can't really see a world where OpenAI's actions are justified here. It was Tomek's job to communicate with METR, who were being given si...

This seems extremely sketchy behavior from OpenAI I don't want to pass judgement before hearing OpenAI's side, but I doubt these three are ...

Are you a quant in London? Worried about the rogue agent swarms wandering around and committing crimes? Wondering whether AI is going to end...

If companies want to claim they support sensible regulation they should, you know, actually support the sensible regulation rather than lyin...

Do you want to reduce x-risk from AGI? We're looking for a senior technical program manager for the GDM AGI Safety team. Someone to help the...

Man, I wish EA was anywhere near as influential as our critics think we are. Imagine thinking that we outspend the lobbying and comms effort...

Fantastic video! The HuggingFace incident is the most WTF alignment is a big deal incident I've seen (so far.) I'm glad there's great videos...

I'm loving the era of personalised AI art! Opus 5.5 wrote, composed and made a video for a song about the story of mech interp (and how thi...

How do OpenAI internal models keep getting scarier and less under control? Great work by their monitoring team! https://twitter.com/Marcus_J...