Christopher Lovejoy
① 他说过的话
3 条
一种在这里能运作得很好的模式是,如果你在平台中强制执行一个更宽泛的 agent 定义,把 LLM 和人类都囊括在内,那么你就可以做到让任何 LLM 能执行的动作,人类也能执行。
指向原始笔记的链接
One pattern that can work very well here is if in your platform you enforce a wider definition of agent which encompasses both LLMs and humans, then you can make it such that any action that can be taken by an LLM could also be taken by a human.
—— Christopher Lovejoy · [13:49]
实际上几乎作为副产品就给了你有效的隐私保护的 evals,而不需要在架构旁边额外加上什么东西。
指向原始笔记的链接
Actually give you effective privacy preserving evals almost as a byproduct without needing to kind of bolt something onto the side of your architecture.
—— Christopher Lovejoy · [15:42]
其次,你有这种人类与智能体的等价性,这意味着对于任何任务,你可以让智能体——也就是 LLM 智能体——和人类都执行它,而你们的差异就是你的 eval。
指向原始笔记的链接
Secondly, you have this human agent equivalency, which means that for any task, you could get both the agent, the LLM agent, and the human to perform it, and your difference is your eval.
—— Christopher Lovejoy · [16:16]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Saul Howard · Anthropic · 智能体 · 审计轨迹 · 交易日志 · 事件溯源 · 对象存储 · 零信任 · 提示词注入 · PHI
