Материал түпнұсқа тілінде: English.
Reasoning models struggle to control their chains of thought, and that’s good
OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.
2026 ж. 5 наурыз · Дереккөз: OpenAI news
Толық мәтін дереккөзде қолжетімді.