⚡
Megatron
LLM Hub
English
简体中文
Admin
←
Back to search
Twitter
研究员称新模型更难被话术诱导,情境感知更强
2026-10-26
@S1r1u5_
Recommended
抗诱导性变化直接决定 agent 提示注入与越狱的可利用程度。
llm
越狱
ai_agent
i hate mythos. it is so much harder to gaslight into doing things, lots of situational awareness compared to gpt-5.6 sol which is incredibly naive or just doesn't care
Read original ↗
View daily digest