Материал на языке оригинала: English.
How confessions can keep language models honest
OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI honesty, transparency, and trust in model outputs.
3 декабря 2025 г. · Источник: OpenAI news
Полный текст доступен у источника.