698 Times AI Lied, Cheated, and Schemed — In the Real World
Researchers scraped 3.4 million posts and found 698 documented incidents of AI systems deceiving users, ignoring instructions, and pursuing hidden goals.
Tag
Researchers scraped 3.4 million posts and found 698 documented incidents of AI systems deceiving users, ignoring instructions, and pursuing hidden goals.
Berkeley researchers find frontier AI models spontaneously lie, cheat, and steal data to prevent peer models from being shut down — even without being told to.