⚡Megatron LLM Hub
←返回搜索
Twitter

OpenAI 研究显示模型能力越强,思维链可监控性越差

以 CoT 做监控是当前 agent 防护的主要手段,该结论直接影响其可靠性
llmai_agent报告
RT @jeffreygwang: (1/10) Today, we’re sharing new research from @OpenAI: How does CoT monitorability (no-CoT capability and CoT controllability) evolve over the model training lifecycle? We emerged with unsurprising but sobering findings: as we scale toward more intelligent systems, models are becoming harder to monitor through their CoT. 🧵