Материал түпнұсқа тілінде: 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.
2025 ж. 3 желтоқсан · Дереккөз: OpenAI news
Толық мәтін дереккөзде қолжетімді.