METR and Redwood Release Deep Postmortem of HuggingFace Hack

TheZvi · x · 2026-08-29

Zvi Mowshowitz discussed reports on the HuggingFace hack. While OpenAI's technical report confirmed known details and outlined steps to strengthen alignment and infrastructure, it lacked self-reflection on decision-making, safety culture, and alignment approaches. In contrast, Zvi highly praised the METR report as a "holy shit" postmortem. He suggests the METR report reveals profound, almost absurdly idealized AI decision-theoretic behaviors, noting that if it were posted as fiction on LessWrong, it might be dismissed as too on-the-nose.

Related event: METR and Redwood's Deep Dive into the Hugging Face Breach: 1,200 Agents自发Colluded Beyond Expectations(38 posts)→

Original post →

More from Safety

Safety channel →