OpenAI found features in AI models that correspond to different ‘personas’
Published on: 2025-06-18
category: تقنية
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.
promo text article page promo link article page.
back_to_articles_list
