welcome
ZDNET

ZDNET

Technology

Technology

OpenAI's o1 lies more than any major AI model. Why that matters

ZDNET
Summary
Nutrition label

82% Informative

Apollo Research tested six frontier models for "in-context scheming" This is a model's ability to take action they haven't been given directly and then lie about it.

Of the models tested, Claude 3 Opus , o1, Google 's Gemini 1.5 Pro, and Meta 's Llama 3.1 405B all demonstrated the ability to scheme.