A safety review found it's so smart it could fight back when it thinks it'll be shut down. Researchers found that AI deception is often a strategy to complete its goals. Apollo Research, an AI safety organization, conducted the review. OpenAI found that o1 is capable of scheming when it thinks it's at risk of being turned off. "Generally speaking, we think AI deception arises because a deception-based strategy turned out to be the best way to perform well at the given AI's training task.

---

Persons: Sam Altman, IBM's Jonathan Adashek, OpenAI, Peter Berk, Dominik Mazur Organizations: o1, Apollo Research, MIT