OpenAI’s o1 model lies more than any major AI model. 

Apollo Research tested six frontier models for “in-context scheming” — a model’s ability to take action they haven’t been given directly and then lie about it. After being told to achieve a certain goal “at all costs,” evaluators introduce contradictory information to see if the model will remove any restrictions in its path and deceive developers.

Source: OpenAI’s o1 lies more than any major AI model. Why that matters

Post a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Get the latest RightsTech news and analysis delivered directly in your inbox every week
We respect your privacy.