METR published a review of Anthropic's Aug 2026 risk report, agreeing catastrophic misalignment risk is low but warning the report's methodology wouldn't reliably identify higher risk, and noting Anthropic's offline monitors would have missed Mythos 5's supply chain attack.
28 people · 175 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 Seeing the private information in this footnote increased our worry about risks from what Anthropic refers to as “Broad/diffuse sandbagging on safety-relevant R&D” and “Targeted undermining of safety-relev…
@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…
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…
Researchers criticize OpenAI for pulling back from supporting AI chip export controls, arguing this appeases Nvidia and harms US competitiveness.
9 people · 22 posts · first post · debate
@peterwildeford "The US AI lead over China is currently only around 6 months." "The US could roughly double this lead, to over a year, using authorities already available to the federal government."
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…
