Adit Abraham
① 他说过的话
3 条
我们做的很多工作和获得的经验,都处在一个更大的主题背景下:AI 应用的范畴最近发生了很大变化,从单纯的信息综合产品变成了真正在干活的智能体。
指向原始笔记的链接
And I think a lot of the work that we’ve done and a lot of the learnings we’ve had are in this sort of broader thematic context of the scope of AI applications has changed a lot recently from just like information synthesis products to actual agents doing work.
—— Adit Abraham · [01:59]
于是我们发现,低于一亿参数的模型在检测文档版面这类事情上非常有效。
指向原始笔记的链接
And so we find that sub 100 million parameter models are really effective for things like detecting the layout of a document.
—— Adit Abraham · [08:43]
最后一点,也许是本次演讲中最重要的一点:归根结底,评估应该成为你所有决策的基础,这一直是我们思考产品的重要部分。
指向原始笔记的链接
The last thing and maybe the most important thing from this talk is that I think at the end of the day evals should underpin all of your decisions and it’s been a big part of how we think about our product.
—— Adit Abraham · [19:01]
② 出现在这些集
1 集
- 《智能体时代,你的 PDF 数据管道拖后腿了吗》 — 作为嘉宾
③ 他谈到的
点进去有真内容 —— 本页主要出口
Reducto · 智能体 · RAG · PDF · VLM · OCR · harness · 评估 · 嵌入模型 · 目标检测
