By Michelle Starr
Publication Date: 2025-12-24 11:00:00
It’s one of humanity’s scariest what-ifs: that the technology we develop to improve our lives is developing a will of its own.
Initial reactions to a September preprint describing the behavior of AI have already speculated that the technology shows a drive to survive. But while it is true that several large language models (LLMs) have been observed actively resisting shutdown commands, the reason is not “will.”
Instead, a team of engineers at Palisade Research suggested that the mechanism is more of a drive to complete an assigned task – even if the LLM is specifically told to turn itself off. And that could be even more worrying than trying to survive, because no one knows how to stop the systems.
Related: AI has already become a master of lies and deception, scientists warn
“These things are not programmed… no one in the world knows how these systems work,” physicist Petr Lebedev, a spokesman for Palisade Research, told ScienceAlert. “There is none…