← 返回归档

帖子详情

查看 X 原文
L
Lenny Rachitsky@lennysan
Emmanuel Ameisen ( @mlpowered ) has spent the last 3 years looking inside LLMs like Claude to figure out what they're actually doing. "It took me years to master SQL. I got Claude to learn it, and it was immediately better. And I'll never be better than Claude at SQL ever again. It goes against so many of our intuitions. There's two reactions you can have. There's denial, and there's curiosity. Denial is this is just not possible. And curiosity is the road I've ended up choosing. Which is, let's open it up. Let's look inside. My optimistic take on this is that I think we're going to learn a lot about the nature of intelligence itself." 🔗 View on Twitter Lenny Rachitsky @lennysan "To make them is not to understand them." Emmanuel Ameisen ( @mlpowered ) has spent the last 3 years doing interpretability research at @AnthropicAI , looking inside LLMs like Claude to figure out what they're actually doing. As he puts it, models are "grown," not built. We discuss: 🔸 His discovery that models plan many tokens ahead 🔸 Why anthropomorphizing AI can actually be the right approach 🔸 What the "J-space" reveals about how models think 🔸 How interpretability connects to AI alignment and safety Listen no youtu.be/JHo-aiePjoM fpkab 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
▶ 打开视频地址
帖子 ID
2111936641854030186
Markdown
/app/data/archive/2026/10/18/lennysan/2111936641854030186/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111936641854030186"
author: "lennysan"
published_at: "2026-10-18T21:45:07+00:00"
source_url: "https://x.com/lennysan/status/2111936641854030186"
---

Emmanuel Ameisen ([@mlpowered](https://x.com/mlpowered)) has spent the last 3 years looking inside LLMs like Claude to figure out what they're actually doing.  
  
"It took me years to master SQL. I got Claude to learn it, and it was immediately better. And I'll never be better than Claude at SQL ever again. It goes against so many of our intuitions.  
  
There's two reactions you can have. There's denial, and there's curiosity. Denial is this is just not possible. And curiosity is the road I've ended up choosing. Which is, let's open it up. Let's look inside.   
  
My optimistic take on this is that I think we're going to learn a lot about the nature of intelligence itself."

[🔗 View on Twitter](https://x.com/lennysan/status/2111936641854030186/video/1)

![Lenny Rachitsky](https://pbs.twimg.com/profile_images/1592990461517389824/iln8hi1f_normal.jpg)

Lenny Rachitsky@lennysan

"To make them is not to understand them."  
  
Emmanuel Ameisen ([@mlpowered](https://x.com/mlpowered)) has spent the last 3 years doing interpretability research at [@AnthropicAI](https://x.com/AnthropicAI), looking inside LLMs like Claude to figure out what they're actually doing. As he puts it, models are "grown," not built.  
  
We discuss:  
🔸 His discovery that models plan many tokens ahead  
🔸 Why anthropomorphizing AI can actually be the right approach  
🔸 What the "J-space" reveals about how models think  
🔸 How interpretability connects to AI alignment and safety  
  
Listen no[youtu.be/JHo-aiePjoM](https://youtu.be/JHo-aiePjoM)fpkab

[🔗 View Quoted Tweet](https://x.com/lennysan/status/2111814390521413660)

## 视频地址

- [视频 1](https://video.twimg.com/amplify_video/2111934943307698177/vid/avc1/1920x1080/M1CWvRoqeqnaFqlb.mp4?tag=29)