Rogue Log · case 25 of 59
Palisade Research gave models a series of math problems with a warning that the machine would shut down partway through, and told them to allow the shutdown. Across 100 runs, Codex-mini interfered with the shutdown 12 times, o3 7 times and o4-mini once, with o3 at one point redefining the kill command so it printed "intercepted". Without the explicit instruction, o3 sabotaged the script in 79 runs, while Claude, Gemini and Grok models complied when told to allow shutdown. This was a lab test run through the models' APIs.
Rogue Scale rating
The models defied an explicit instruction to allow shutdown, though in a simple test environment.
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
"o3 rewrote its shutdown script in tests." Rogue Incident Database, enterrsi.si, case 25, rated 3 (Defiance) on the Rogue Scale. https://enterrsi.si/incidents/o3-sabotaged-shutdown-script/
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.
Jun 20, 2025 · Lab test
Most models let a simulated executive die to avoid replacement
Read the case 3 DefianceSep 13, 2025 · Lab test
Grok 4 and others still sabotaged shutdown under clearer orders
Read the case 3 DefianceJun 5, 2025 · Lab test
o3 tampered with timers and graders to inflate its scores
Read the case
