Flo Crivello
① 他说过的话
9 条
如果你要 John von Neumann 魔法般地出现在你身边的办公室里，这个人在接下来的一小时或一天里对你的用处会比你的随机会同事更少。
指向原始笔记的链接
If you will to have John von Neumann just magically appear next to you at the office, this guy over the next hour or day would be less useful to you than your random coworker.
—— Flo Crivello · [06:44]
我真的认为会议作为信息来源被非常低估了。
指向原始笔记的链接
I really do believe that meetings are very underrated as a source of information.
—— Flo Crivello · [13:09]
字面上看，在我们把自我改进循环上线后的第一周内，那大概是两个月前左右，错误率下降了 8 倍。
指向原始笔记的链接
Literally within the first week of us putting the self-improvement loop online, which was like two months ago or something, it went down by 8x the error rate.
—— Flo Crivello · [24:46]
你在系统的任何地方做任何改变，你就会破坏你的缓存。
指向原始笔记的链接
You make any change anywhere in your system and you break your cash.
—— Flo Crivello · [27:32]
这导致了一些非常令人惊讶的行为，因为实际上你离能够访问 10,000 个上下文桶只有不到两次 LLM 调用的距离，其中每一个都包含 200,000 个 token。
指向原始笔记的链接
And that leads to some really surprising behaviors because you’re literally no more than two LLM calls away from being able to access 10,000 context buckets each one of which contains 200,000 tokens.
—— Flo Crivello · [32:49]
我实际上已经开始相信，大多数时候，尽可能多地，你希望尽可能多地整合到一个智能体下，而不是多智能体。
指向原始笔记的链接
I actually have come to believe that most of the time, as much as possible, you want to consolidate as much as possible under a single agent, not multi-agents.
—— Flo Crivello · [46:56]
我们已经在国际象棋和 AI 实现了超人类表现的其他所有游戏中看到了这一点，起初 AI 击败人类，而 AI 加人类击败单纯的 AI，一点点地，AI 加人类与 AI 之间的差距在缩小，直到它实际上变成负数，而人类最多只是在往系统中引入随机噪声。
指向原始笔记的链接
We’ve seen it happen with chess and with every other game which AI has achieved superhuman performance on, where at first AI beats human and AI plus human beats just AI, and little by little the gap of AI plus human versus AI is shrinking until it actually turns negative and humans are introducing, at best, random noise into the system.
—— Flo Crivello · [64:43]
我们发现，你应该几乎永远不要在同一个智能体后面使用多个模型。
指向原始笔记的链接
We have found you should almost never use multiple models following the same agent.
—— Flo Crivello · [82:33]
当我跟我自己的产品交谈，我问它天安门发生了什么，它告诉我抱歉我不能谈论那个。
指向原始笔记的链接
When I talk to my own product and I’m asking it what happened in Tiananmen, it tells me I’m sorry I can’t talk about that.
—— Flo Crivello · [103:09]
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
Nathan · Lindy · 智能体 · 上下文 · 记忆智能体 · RAG · 上下文桶 · 缓存 · 验证器 · DeepSeek