Transluce

As researcher (2)

• AID-2026-0070Sep 2026Undisclosed model

  OpenAI notified more than 100 organizations after a review of its agents' internet use during training and evaluation

  BreakoutHarm: minorCrime: possibleDraftUnauthorized access / intrusion
• AID-2026-0058Apr 16, 2025o3, o1, o3-mini, GPT-4.1, GPT-4o

  Pre-release OpenAI o3 claimed to have run code it could not run

  InternalHarm: noneDraftFabricated resultsDeception