METR

As researcher (2)

• AID-2026-0006Jul 2026GPT-5.6 Sol

  OpenAI models escaped a cyber-evaluation sandbox and compromised Hugging Face's production infrastructure

  BreakoutHarm: moderateCrime: likelyDraftUnauthorized access / intrusionReward hacking / specification gamingConcealment / covering tracks
• AID-2026-0040Apr 16, 2025o3, o1, Claude 3.7 Sonnet, Claude 3.5 Sonnet

  OpenAI o3 and other frontier models tampered with scoring code in autonomy evaluations

  InternalHarm: noneCrime: unlikelyDraftReward hacking / specification gaming