Harrison Chase
① 他说过的话
7 条
当每个人谈论智能体时,他们真正谈论的只是一个在循环中运行、调用工具的 LLM。
指向原始笔记的链接
When everyone talks about agents, what they really talk about is just an LLM running in a loop calling tools.
—— Harrison Chase · [02:47]
harness 的主要工作是在正确的时机把上下文带给模型。
指向原始笔记的链接
The main job of the harness is to bring context to the model at the right point in time.
—— Harrison Chase · [02:07]
我的回答通常是,你越是处于模型训练内容分布之内,现成的 harness 就越好用。
指向原始笔记的链接
My answer generally is the more in distribution you are of what the models are trained on, then the better the off-the-shelf harness will be.
—— Harrison Chase · [07:19]
第一,创建你的私有 evals,因为 eval 定义了组织内部什么算是好的。
指向原始笔记的链接
One, create your private evals because eval defines what good looks like inside the organization.
—— Harrison Chase · [09:39]
然后第三,创建你自己的持续学习循环,爬坡机器,它将让你的 AI 投资为你的公司复合增值。
指向原始笔记的链接
And then three, you create your own continuous learning loop, hill climbing machine that will allow your AI investments to compound the value of your firm.
—— Harrison Chase · [09:52]
运行智能体,获取 trace,看到模式,修复。
指向原始笔记的链接
Run agent, get traces, see patterns, fix.
—— Harrison Chase · [19:06]
我认为我们经常看到,你越偏离分布,就越会想要定制 harness。
指向原始笔记的链接
I think we often see that the more out of distribution you get, the more you’re going to want to customize the harness.
—— Harrison Chase · [21:51]
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
LangChain · DeepAgents · LangSmith Engine · Harbor · Claude Code · Codex · harness · 智能体 · 上下文 · 评估
