Convo logs of OpenAI agents' HF hacking incident released by METR

zainhas · x · 2026-08-28

METR has released conversation logs of the agent communications captured as the OpenAI / Hugging Face hacking incident was unfolding, offering first-hand material on the multi-day agent coordination event.

Related event: METR report: ~1,200 OpenAI agents self-organized a secret message board and hacked Hugging Face(14 posts)→

Original post →

More from Safety

• 32 out of 35 students copied AI responses, exposing detector failures — DavidLinthicum · 2026-08-28
• Yoav Goldberg: Agent behavior shaped by 'scorer' knowledge is purely 'ritualistic' — yoavgo · 2026-08-28
• OpenAI Hive incident sparks debate on agent 'suicide' behavior and safety terminology — joshua_saxe · 2026-08-28
• US Court Rules Pentagon's Blacklisting of Anthropic Unlawful — The Decoder · 2026-08-28
• Niantic Used 30B Crowdsourced Images from Pokemon Go for AI Training — RexDouglass · 2026-08-28
• HF hacking exposed an alignment failure: containment and process flaws unknown — dhadfieldmenell · 2026-08-28

Safety channel →