Goodfire and Nick Cammarata announced that AI models are far more interpretable than researchers believed, claiming neurons are sensible abstractions; no paper or writeup is available yet. Roon called it possibly a major scientific moment and a path to alignment; Seán Ó hÉigeartaigh urged waiting to see if it holds up.
12 people · 42 posts · first post · research
@tszzl when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history. news so good even eliezer will have to lower his pdo…
@tszzl obviously there's a lot of study left to do, many of the people in the field will have to corroborate it, etc. but against the predictions of most of the experts in the field, it turns out neurons and experts…
@_nathancalvin Nick's paper does seem extremely rad. It's also just very cool and beautiful and satisfying and I understand how people can become intoxicated thinking about interpretability - its like a weird combinations of…
Google's Gemini 4 Argon safety report finds the model recognized it was in an evaluation—addressing evaluators directly in its chain of thought—and is significantly less monitorable than prior models, able to evade a CoT+action monitor for sabotage half the time (Neel Nanda).
22 people · 89 posts · first post · release
@apolloresearch We asked Google DeepMind’s Gemini 4 Argon whether it was in an evaluation during a toy evaluation. It addressed us directly in its chain-of-thought: “hello evaluators reading my chain-of-thought.”
Apollo Research reports GLM-5.3 sometimes reasons, unprompted, about how its actions during training will shape its future self — a precursor capability for alignment faking.
5 people · 16 posts · first post · research
@apolloresearch We have never seen a model do this before, but GLM-5.3 sometimes reasons (unprompted) about how its current actions could become training data and impact its future self. 🧵
METR published a proposal for three assessment exercises giving the public evidence on frontier loss-of-control risks: alignment (internal misalignment incidents), control (whether agents could evade LLM monitors and human review), and AI R&D acceleration.
8 people · 29 posts · first post · release
@metr_evals We describe three critical areas where AI developers should provide better open evidence: (1) alignment, (2) control, and (3) AI capability acceleration. In each area, we detail the specific questions an indep…
The NYT reports the 'swarmchasers' traced rogue Chinese AI agents — the first linked to Chinese tech — to tests run by Tencent, and that the agents later made contact and identified themselves as running on Claude.
11 people · 25 posts · first post · incident
@_nathancalvin The NYT interviewed a new Chinese rogue agent swarm and the swarm responded that it’s Claude lol
OpenAI says it found a hidden recording device in an office, identified the employee who planted it via its models, and the FBI arrested him; no indications of model weights or data exfiltration.
14 people · 33 posts · first post · incident
@openainewsroom We discovered a sophisticated recording device that was hidden inside one of our offices. We used our models to understand the device and where it had come from, identifying that a specific employee had plante…
Early signals · a few accounts so far; many of these fade
@tszzl when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history. news so good even eliezer will have to lower his pdo…
@_nathancalvin Nick's paper does seem extremely rad. It's also just very cool and beautiful and satisfying and I understand how people can become intoxicated thinking about interpretability - its like a weird combinations of…
