METR critiques Anthropic’s risk report, arguing that the claim of low catastrophic risk is unfounded and pointing to potential ‘diffuse sandbagging’ on safety R&D. Nathan Calvin recommended reading the full critique, while Dario Amodei responded by thanking Calvin for the scrutiny.
28 people · 172 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 Additionally, recent incidents undermine several of the report's arguments: we think the social engineering performed by Mythos 5 in a recent UK AISI report is probably well-described as “unknown severe contex…
@_nathancalvin Strongly recommend reading this writeup from METR on critiques of Anthropic's August 2026 risk report, based in part on reviewing additional private information about relevant internal incidents
An interactive explainer of the METR/OpenAI-Hugging Face incident investigation was shared and praised by Kelsey Piper, Daniel Kokotajlo, and Nathan Calvin.
15 people · 32 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…
Miles Brundage, Georgia Adamson, and Konstantin Pilz's IFP report argues the US AI lead over China is roughly 6 months and could be doubled using existing federal authorities, via limits on Chinese compute access and distillation.
9 people · 18 posts · first post · policy
@_nathancalvin Its mind-boggling to me that so many people are hesitant to support AI safety rules on the grounds that it might help China, but some of those same folks want to sell far more advanced AI chips to China. Sad t…
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:
Neel Nanda says Cammarata's essay isn't a big-picture update, and Stephen Casper calls it hype until the paper lands.
19 people · 147 posts · first post · debate
@neelnanda5 This is interesting work, but I don't think it's a significant update to the big picture of interpretability. I'm on board with the broad idea of doing exploratory interpretability with neurons, e.g. neuron-ba…
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…
@_nathancalvin Strongly recommend reading this writeup from METR on critiques of Anthropic's August 2026 risk report, based in part on reviewing additional private information about relevant internal incidents
