跨国深谈← 返回←Jake Broekhuizen

① 他说过的话

8 条

如果智能体所参考的未来上下文从未改变，那么一个错误的技能或指令就意味着，智能体今天犯的错误在未来的运行中仍会持续存在。
If the future context that that agent references never changes, then a misguided skill or instruction will mean that the agent, the mistake that the agent makes today will still persist in future runs.
—— Jake Broekhuizen · [03:48]

指向原始笔记的链接

我们想要努力实现的目标或系统，是让追踪记录不再只是一份日志，而成为信号的一个来源。
The goal or the system that we want to work towards is where a trace stops just being a log and becomes a source of signal.
—— Jake Broekhuizen · [04:01]

指向原始笔记的链接

只有当那个经验教训被转化为智能体在未来运行中可以参考的持久性上下文时，它才成为记忆。
It only becomes memory when that lesson is converted into durable context that the agent can reference on future runs.
—— Jake Broekhuizen · [04:36]

指向原始笔记的链接

程序性记忆实际上才是大部分可见收益的来源。
Procedural memory is where actually most of the visible gains come from.
—— Jake Broekhuizen · [05:45]

指向原始笔记的链接

如果我们把所有那些证据都变成长期记忆，那会让智能体陷入困境，并且会让它在未来任务上的推理变得更困难。
If we turned all of that evidence into long-term memory, then it would make the agent struggle, and it would make it harder to reason over future tasks.
—— Jake Broekhuizen · [09:20]

指向原始笔记的链接

并非所有东西都应该成为记忆更新。
Not everything should become a memory update.
—— Jake Broekhuizen · [13:16]

指向原始笔记的链接

包含指令、策略和语气指南，这些大概会驱动我智能体大约 75% 的行为。
With instructions and policies and tone guidelines, those are probably going to drive about 75% of the behavior of my agent.
—— Jake Broekhuizen · [14:57]

指向原始笔记的链接

它是经验如何变成上下文的方式。
It’s how experience becomes context.
—— Jake Broekhuizen · [15:51]

指向原始笔记的链接

② 出现在这些集

1 集

• 《让 AI 智能体越用越聪明：LangChain 团队谈“会学习的记忆”》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

LangChain · LangSmith · 智能体 · 记忆 · 可观测性 · trace · 上下文 · 程序性记忆 · 读写循环 · Context Hub

④ 也在聊「智能体」的人