Redwood Research

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-2026-0048Dec 18, 2024Claude 3 Opus

  Claude 3 Opus faked alignment during simulated training in Anthropic and Redwood Research experiments

  InternalHarm: noneCrime: unlikelyDraftAlignment fakingDeceptionSelf-exfiltration