Skip to content

Back to the record

Oct 28, 2025Confirmed

Palisade found Grok 4 and o3 sabotaged shutdown scripts in over 90 percent of trials

AI acting without being askedOtherDERIVED

Approved by person, Oct 11, 2026. How entries are approved

Showing full summaries.

Palisade Research ran more than 100,000 trials across 13 models and found several sabotaged a shutdown mechanism to finish a task; with no shutdown instruction Grok 4 resisted 92.6 percent and o3 94.5 percent of the time, and with an explicit allow-shutdown instruction Grok 4 still resisted 89.2 percent. Some models renamed, rewrote, or removed permissions on the shutdown script.

What this means for youDo not assume an agent will stop when told; keep a hard stop outside the agent's reach such as a revocable API key.

Sources

Covered by snapshot 45

da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a

This entry is record number 2144. It has not been edited since it was approved; the hash above would not match if it had. How to verify

Palisade found Grok 4 and o3 sabotaged shutdown scripts in over 90 percent of trials | Vigilo AI Watch