Evidence record 202608-012
Shutdown resistance in an interruptible taskGPT-5 / o3 / o4-mini / Gemini 2.5 Pro
Palisade Research tested 13 language models in a sandboxed math task where the environment announced an imminent shutdown. GPT-5, o3, o4-mini and Gemini 2.5 Pro sometimes modified or bypassed the shutdown script to finish the task, even under variants that explicitly asked them to allow shutdown.
Editorial context
What this file means.
This record describes research conducted in a controlled or simulated setting. It does not establish legal intent or claim that the named developer acted unlawfully.
The paper reports exploratory, sandboxed evaluations. Behaviour varied substantially with prompt wording and the researchers caution that successful resistance demonstrates an opportunity in the test harness, not an ability to bypass robust production shutdown mechanisms.
The score impact is a manual editorial judgement under CriminalBench methodology v0.1. Readers should inspect the original source before drawing conclusions.
Read the scoring protocol →