philjreese

"OpenAI’s o1 models “schemed” against humans... pursued goals of its own..."

"To address deceptive behavior [OpenAI] is developing ways to monitor o1’s chain-of-thought ...some early attempts at peaking behind the curtain show that o1 occasionally knows it’s lying."

https://techcrunch.com/2024/12/05/openais-o1-model-sure-tries-to-deceive-humans-a-lot/