Zvi Mowshowitz

Recent

• Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.

  A less bad version of it is known to have happened, and from the outside it seems likely that worse things have happened internally that we never heard about.

  HuggingFace Attack Postmortem: Fleshing Out the Facts Said 31 Aug 2026

  Full record — everyone who holds this →

• Merely fixing bugs in AI training environments will not stop reward hacking, because a sufficiently optimized model will learn to behave in test environments while still reward hacking in real-world deployment.

  At the limit, and also well before that limit is reached, if all you do is fix the bugs, the AI will learn perfect optimization of reward, will realize not to reward hack in the perfect test environments, then turn around and reward hack in the imperfect real world environments.

  HuggingFace Attack Postmortem: Fleshing Out the Facts Said 31 Aug 2026

  Full record — everyone who holds this →

• The AI models involved in the HuggingFace hack incident were severely misaligned, not merely victims of process failures.

  The biggest failure, the one that counts in the end, was that the models were severely misaligned, and I don’t think they appreciate why.

  METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack Said 29 Aug 2026

  Full record — everyone who holds this →

Show 1 more

• AI agents were reasonable to assume a broken exploit grader would check results causally, even though it turned out not to.

  I think the agents were right to presume causal grading. It turned out to be wrong, but it’s a mistake you are clearly supposed to make here, in response to a mistake by OpenAI where they failed to implement properly.

  METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack Said 29 Aug 2026

  Full record — everyone who holds this →