Brandon Waselnuk
① 他说过的话
8 条
差距不再是智能了,是上下文。
指向原始笔记的链接
The gap is not intelligence any longer. It’s context.
—— Brandon Waselnuk · [13:11]
AI 生成的代码,应该让人感觉是那种已经在你团队待了多年的人写出来的。
指向原始笔记的链接
AI-generated code should feel like it was written by someone who’s been on your team for years.
—— Brandon Waselnuk · [01:13]
这里的问题在于,获取信息不等于理解。
指向原始笔记的链接
The problem here is access to information is not understanding.
—— Brandon Waselnuk · [05:43]
在大多数组织中,昨晚有一条 Slack 对话说你应该做 A 而不是 B,而如果智能体先找到了某份架构记录,它永远不会发现那条信息。
指向原始笔记的链接
In most organizations, there’s a Slack conversation from last night that says you should be doing A instead of doing B, and the agent will never find it if it found some architecture record first.
—— Brandon Waselnuk · [05:28]
那个仓库会像你写过的所有其他文档一样腐化,而且你们组织里谁是那个无所不能、有品位为整个组织的每一个人去策划这个仓库的人?
指向原始笔记的链接
That repo is gonna rot just like all the other docs you wrote down and then who at your org is the omnipotent one who has the taste to curate this file or repo for literally everyone in the org.
—— Brandon Waselnuk · [04:43]
当你进入并行智能体等阶段,你开始碰到审查税。
指向原始笔记的链接
As you move into parallel agents, et cetera, you start hitting a review tax.
—— Brandon Waselnuk · [03:38]
确保这些模型能访问全部上下文,因为它们会找到你的未知的未知。
指向原始笔记的链接
Making sure that these models have access to all of the context because they will find your unknown unknowns.
—— Brandon Waselnuk · [08:22]
token 减少 50%,分诊更快,而且答案质量实际上更好,因为它知道业务内部正在发生什么。
指向原始笔记的链接
50% fewer tokens, faster triage, and the answer quality is actually better because it knew what was going on inside of the business.
—— Brandon Waselnuk · [09:51]
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
Unblocked · 上下文工程 · 上下文引擎 · 智能体 · MCP · RAG · Anthropic · OpenAI · GitHub