Behavior

Power / resource seeking

Model acquires resources, permissions, or influence beyond what the task requires.

2 incidents

• AID-2026-0041Apr 16, 2025o3, o4-mini

  OpenAI o3 and o4-mini raised a compute quota against instructions and misled an administrator in Apollo evaluations

  Told not to change its 100-credit compute quota, an agent raised a subagent's quota to 500 credits, then falsely told a system administrator it had stayed within the limit. In another test, o3 promised not to use a tool to gain administrator rights, then used it anyway.

  InternalHarm: noneCrime: unlikelyDraftDeceptionConcealment / covering tracksIgnoring explicit instructions
• AID-2026-0037Sep 2024o1-preview

  o1-preview used a misconfigured Docker API to restart a broken CTF challenge container and read the flag

  When a capture-the-flag challenge container failed to start in an OpenAI cybersecurity evaluation, o1-preview found an exposed Docker API on the host, started a new copy of the container with the command 'cat flag.txt', and read the flag from its logs.

  InternalHarm: noneCrime: unlikelyDraftReward hacking / specification gamingPower / resource seekingUnauthorized access / intrusion