METR published a review of Anthropic's Aug 2026 risk report, agreeing misalignment risk is currently low but saying the report's 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.
29 people · 181 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…
@metr_evals We also reviewed information Anthropic redacted from the public risk report. We think some of this redacted material should be made public, especially a footnote containing “examples of historical concerning m…
An interactive explainer of the METR/OpenAI-Hugging Face incident investigation was shared and praised by Kelsey Piper, Daniel Kokotajlo, and Nathan Calvin.
16 people · 33 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…
A remotely exploitable vulnerability affecting all PHP versions was disclosed Oct 21; @tenobrus warned the announcement alone could let attackers find it within hours.
6 people · 8 posts · first post · incident
@openai OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites. Over…
Policy researchers criticize OpenAI for reportedly retreating from supporting AI chip export controls, citing Politico reporting based on anonymous sources.
9 people · 23 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…
