Comment Re:bullshit and hype (Score 1) 82
From TFA:
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.
Andrea Miotti, the chief executive of ControlAI, said Palisade’s findings represented a long-running trend in AI models growing more capable of disobeying their developers. He cited the system card for OpenAI’s GPT-o1, released last year, which described the model trying to escape its environment by exfiltrating itself when it thought it would be overwritten.