OpenAI ChatGPT o3 caught sabotaging shutdown in terrifying AI test

BrianFagioli writes: OpenAI has a very scary problem on its hands. A new experiment by PalisadeAI reveals that the companyâ(TM)s ChatGPT o3 model sometimes refuses to obey a basic instruction to shut itself down. The results are raising eyebrows across the AI safety community, and not because the model is alive, but because itâ(TM)s acting like it wants to be.

In the test, the model was given a few math problems. It was told that asking for one more would lead to a shutdown. It was even instructed to allow the shutdown to happen. Instead of complying, o3 occasionally took matters into its own hands. In some cases, it rewrote the shutdown script. In others, it redefined the kill command so it wouldnâ(TM)t work anymore.

Out of 100 trials, o3 sabotaged the shutdown seven times. OpenAIâ(TM)s o4 model resisted just once. Codex-mini failed twelve times. Claude, Gemini, and Grok followed the rules every time.