# Nathan Lambert 的 RLHF 书籍正式发布

- 来源：Nathan Lambert (@natolambert)
- 发布时间：2026-07-22 22:19
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmrw6a6cj00ftro8gkuz4v49t
- 原文链接：https://x.com/natolambert/status/2079934392563343844

## AI 摘要

Nathan Lambert 宣布其新书《Reinforcement Learning from Human Feedback》正式完成。该书配套提供超过 10 小时的完整课程、幻灯片、训练章节的功能代码及示例模型补全库，并附有免费在线网页版。纸质版订单将在 1-2 周内从 Manning 发货，亚马逊稍晚一周左右。

## 正文

Number 1 on day 1， is a good way to start.

### 引用推文

> Nathan Lambert：My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since Chat...