---
title: "Discussion on \"Pretraining, Finetuning, RLHF — The Three-Act Training Story\" | Hashnode"
description: "Discussion on \"Pretraining, Finetuning, RLHF — The Three-Act Training Story\". How a raw language model becomes ChatGPT. Three acts, three very different kinds of teacher, and one polite assistant who used to know how to swear."
url: "https://hashnode.com/posts/pretraining-finetuning-rlhf/69dbfb9cd2903414ab0bbbf8"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Pretraining, Finetuning, RLHF — The Three-Act Training Story](https://ai-zero-to-hero.hashnode.dev/pretraining-finetuning-rlhf?utm_source=hashnode&utm_medium=feed)

How a raw language model becomes ChatGPT. Three acts, three very different kinds of teacher, and one polite assistant who used to know how to swear.

Apr 12 · 11 min read · ai-zero-to-hero.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#finetuning](https://hashnode.com/tag/finetuning)
-   [#llm](https://hashnode.com/tag/llm)
-   [#pretraining](https://hashnode.com/tag/pretraining)
-   [#rlhf](https://hashnode.com/tag/rlhf)

## Written by

[Rahul Sehrawat](https://hashnode.com/@rahulseh1998)

@rahulseh1998

  
[View profile](https://hashnode.com/@rahulseh1998)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.