Hamad Bashir
① 他说过的话
8 条
智能体的查询频率不是人类的频率，而是智能体式的频率。
指向原始笔记的链接
And the agents don’t query at a human rate, they query at an agentic rate.
—— Hamad Bashir · [11:19]
通过运行这些实验，你很快会看到在几万 token 的量级上出现极其陡峭的性能下滑。
指向原始笔记的链接
And by running these experiments, what you quickly see is a super sharp drop off in the tens of thousands of tokens.
—— Hamad Bashir · [13:38]
模型在区分两个并不矛盾、但都是关于同一件事的事实时相当糟糕。
指向原始笔记的链接
So models are quite bad at disambiguating between two facts that aren’t in contradiction but that are about the same thing.
—— Hamad Bashir · [17:30]
在大多数情况下，你并不需要那么多原始智能，你更需要的是能非常快速地做大量这些事情的能力。
指向原始笔记的链接
And in most cases, you don’t need that much raw intelligence as much as you need the ability to do a lot of that very quickly.
—— Hamad Bashir · [23:11]
用大模型来调度一支更小模型的舰队，我认为这是我们相当坚定信奉的范式，它已经被证明是编码系统的运作方式，而且我认为在未来一年它会进入几乎每一个智能体。
指向原始笔记的链接
Over a fleet of smaller models is I think a paradigm that we believe in quite firmly and it’s already proving out to be how coding systems will work and I think it’ll find its way into almost every agent over the coming year.
—— Hamad Bashir · [24:29]
仅仅是让模型并行进行工具调用，就能给它带来巨大的优势，让它能非常快速地减少发现信息所需的轮次。
指向原始笔记的链接
Even just getting the model to tool call in parallel gives it a huge advantage in its ability to very quickly reduce the number of turns that it needs in order to discover information.
—— Hamad Bashir · [31:31]
所以在稳态下，一个更大的语言模型大概总是会胜过更小的模型，但小模型用 LoRA 微调足够便宜，以至于在足够窄的语料库上，你也可以非常快地微调一个小模型，让它在个性化语料库上变得更好，并为特定任务对模型进行个性化。
指向原始笔记的链接
And so a larger language model will probably always outperform a smaller one at steady state, but the smaller ones are cheap enough to fine tune using LoRa that on narrow enough corpuses, you can very quickly also fine tune a small model on a narrow corpus and make it better at individualized corpuses and personalize the model for specific tasks.
—— Hamad Bashir · [32:22]
而会是智能真正运行在数据库内部。
指向原始笔记的链接
It’ll be intelligence actually runs inside of the database.
—— Hamad Bashir · [49:09]
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
Gregor Vand · Chroma · ChromaDB · Context 1 · 上下文腐烂 · 智能体搜索 · 向量搜索 · 上下文工程 · 小模型 · BYOC