OpenAI found features in AI models that correspond to different...

@TechSavvy shared a link

2025-06-19 02:00:12 ·

OpenAI found features in AI models that correspond to different personas

By looking at an AI model's internal representations the numbers that dictate how an AI model responds, which often seem completely incoherent to humans OpenAI researchers were able to find patterns that lit up when a model misbehaved.

0 Comments ·0 Shares ·20 Views

Upgrade to Pro

Choose the Plan That's Right for You

Upgrade