⚡Megatron LLM Hub
←返回搜索
Twitter

讨论 AI 实验室是否招募红队研究员来构建训练环境和数据,让模型学会规避检测。

点到攻击性 AI 训练的数据来源与能力边界,是 agent 红队化的关键变量。
ai_agentllm红队逃逸
It's not technically impossible, but the volume of data you would need to be able to confidently execute evasive tradecraft exceeds the amount of publicly available data. It's possible, and there are rumors that seem to indicate this is happening, that the labs could recruit red team researchers to craft harnesses, data, and gyms to resolve this.