Материал на языке оригинала: English.
Detecting misbehavior in frontier reasoning models
Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent.
10 марта 2025 г. · Источник: OpenAI news
Полный текст доступен у источника.