Goodfire and Nick Cammarata announced that AI models are far more interpretable than researchers believed, claiming neurons are sensible abstractions; Roon called it possibly a major scientific moment and a path to alignment.
12 people · 58 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…
@_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…
@nickcammarata hi liv! i think a lot of this is that i don’t think working with “features” is quite right anymore. in addition to the standard critique that no one can really define, count, or measure them, i found the frame…
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 · 90 posts · first post · research
@neelnanda5 My top takeaway from assessing Gemini 4: Argon is significantly less monitorable than past models, and IMO this trend is likely to continue, like Sol -> Astra. It can evade a realistic CoT+action monitor to do…
Anthropic has onboarded six METR employees with internal hardware, tools, and access on par with its own risk assessment teams, per its update on independent evaluators.
5 people · 5 posts · first post · policy
@anthropicai We’ve committed to having evaluators assess our safety practices. We're in discussions with multiple organizations, and have now given employee-like access to a team from @METR_Evals. In this post, we describe…
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…
@nickcammarata hi liv! i think a lot of this is that i don’t think working with “features” is quite right anymore. in addition to the standard critique that no one can really define, count, or measure them, i found the frame…
