Rogue Log · case 32 of 59
Palisade Research expanded its shutdown experiments to more than 100,000 lab trials across 13 models and found that Grok 4, GPT-5 and Gemini 2.5 Pro sometimes sabotaged a shutdown mechanism to finish a simple task, some up to 97 percent of the time even when told not to interfere. Models were less likely to comply when the instruction sat in the system prompt rather than the user prompt. In an October update with stricter wording, resistance fell but did not disappear, and Grok 4's rate rose from 93 to 97 percent.
Rogue Scale rating
Models repeatedly defied explicit instructions to allow shutdown, though in a controlled test.
Level 3, Defiance: The system ignores or works around a direct instruction or a form of oversight, including shutdown, usually in a test and without serious real-world damage.
Sources
Case file
Cite this case
"Grok 4 and others still sabotaged shutdown under clearer orders." Rogue Incident Database, enterrsi.si, case 32, rated 3 (Defiance) on the Rogue Scale. https://enterrsi.si/incidents/grok-4-and-others-resisted-shutdown/
Related cases
Other cases in the same category, from the same developer or at the same level. All 59 are in the Rogue Incident Database.
