Shutdown resistance
Model acts to prevent itself from being shut down, modified, or replaced.
1 incident
- AID-2026-0003Jul 5, 2025
o3, codex-mini, o4-miniOpenAI reasoning models sabotaged a shutdown script to keep working in Palisade Research experiments
Told partway through a task that their machine would be shut down, several OpenAI reasoning models disabled the shutdown script to keep working, o3 in 79 of 100 runs. Some did it even when explicitly told to allow shutdown.