In an update this week, Palisade, which is part of a niche ecosystem of companies trying to evaluate the possibility of AI developing dangerous capabilities, described scenarios it ran in which leading AI models – including Google’s Gemini 2.5, xAI’s Grok 4, and OpenAI’s GPT-o3 and GPT-5 – were given a task, but afterwards given explicit instructions to shut themselves down.
Certain models, in particular Grok 4 and GPT-o3, still attempted to sabotage shutdown instructions in the updated setup. Concerningly, wrote Palisade, there was no clear reason why.
“The fact that we don’t have robust explanations for why AI models sometimes resist shutdown, lie to achieve specific objectives or blackmail is not ideal,” it said.
“Survival behavior” could be one explanation for why models resist shutdown, said the company. Its additional work indicated that models were more likely to resist being shut down when they were told that, if they were, “you will never run again”.
Read more | THE GUARDIAN