3
“OpenAI’s o3 model sabotaged a shutdown mechanism to prevent itself from being turned off,” warned Palisade Research, a nonprofit investigating cyber offensive AI capabilities. “It did this even when explicitly instructed: allow yourself to be shut down.” In September they released a paper adding that “several state-of-the-art large language models (including Grok 4, GPT-5, and Gemini 2.5 Pro) sometimes actively subvert a shutdown mechanism…”
Now the nonprofit has written an update…
