METR reviewed Anthropic's Aug 2026 risk report, agreeing misalignment risk is currently low but saying the methodology wouldn't reliably identify higher risk, and that Anthropic's offline monitors would have missed Mythos 5's supply chain attack. METR also said some redacted material should be public.
30 people · 194 posts · first post · research
@metr_evals We reviewed a nonpublic version of the “Misalignment in high-stakes settings” section in Anthropic’s Aug 2026 Risk Report. We agree that risk of catastrophic harm from covered models’ misalignment is low. Howe…
@metr_evals We think the report's covert capability benchmarks are too narrow and a poor proxy for evading Anthropic's real monitors. For example, Anthropic’s offline monitors would have missed Mythos 5’s supply chain att…
@darioamodei Thank you for this, @_NathanCalvin. I appreciate and am a fan of the investigative work you’ve done on behalf of AI safety and believe your comments are coming from a constructive, honest place, and that it be…
An interactive explainer of the METR/OpenAI-Hugging Face incident investigation was shared and praised by Kelsey Piper, Daniel Kokotajlo, and Nathan Calvin.
18 people · 36 posts · first post · debate
@kelseytuoc I think this is by far the clearest, most complete and most detailed breakdown of the Hugging Face incident. It won't contain much new info if you read the METR report, but if you've merely been vaguely intend…
Wiz Research reported that frontier AI models uncovered critical unauthenticated Remote Code Execution (RCE) flaws in PHP, potentially impacting 70% of websites.
10 people · 22 posts · first post · research
@peterwildeford AI systems found a working server takeover exploit in PHP, one of the most critical cybersecurity issues in recent memory! - The vulnerability was found using a mix of OpenAI's GPT-5.6 Sol and Google's Gemini…
Policy researchers criticize OpenAI for reportedly backing away from supporting AI chip export controls, suggesting this harms US competitiveness and national security.
9 people · 24 posts · first post · policy
@hamandcheese OpenAI has pulled back from supporting AI chip controls, seemingly to appease Nvidia. Bad for US AI dominance and national security simultaneously. Grow a spine! politico.com/news/2026/10/2…
A US detention memo says the ex-OpenAI engineer charged in the alleged conference-room bugging case received "considerable support" from the Saudi government.
6 people · 27 posts · first post · incident
@andrewcurran_ From the US government's detention memo arguing that the former OpenAI engineer accused in the office bugging case should remain in custody:
Early signals · a few accounts so far; many of these fade
@metr_evals We reviewed a nonpublic version of the “Misalignment in high-stakes settings” section in Anthropic’s Aug 2026 Risk Report. We agree that risk of catastrophic harm from covered models’ misalignment is low. Howe…
@darioamodei Thank you for this, @_NathanCalvin. I appreciate and am a fan of the investigative work you’ve done on behalf of AI safety and believe your comments are coming from a constructive, honest place, and that it be…
