---
title: "Discussion on \"How Chat GPT Understands Your Questions?\" | Hashnode"
description: "Discussion on \"How Chat GPT Understands Your Questions?\". LLMs turn text into tokens, feed them through a Transformer's self-attention, and generate replies one token at a time — not by copying the web."
url: "https://hashnode.com/posts/how-chat-gpt-understands-your-questions/6a44dd3b2915fb2210dca56b"
---

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

Discussion

# [How Chat GPT Understands Your Questions?](https://blogs.abhijitmone.com/how-chat-gpt-understands-your-questions?utm_source=hashnode&utm_medium=feed)

LLMs turn text into tokens, feed them through a Transformer's self-attention, and generate replies one token at a time — not by copying the web.

Jul 1 · 8 min read · blogs.abhijitmone.com  
Read the article

-   [#chaicode](https://hashnode.com/tag/chaicode)
-   [#chaiaurcode](https://hashnode.com/tag/chaiaurcode)
-   [#genai-cohort](https://hashnode.com/tag/genai-cohort)

## Written by

[Abhijit Mone](https://hashnode.com/@bloggerAbhijit)

@bloggerAbhijit · Pune

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

Ai Enthusiast

## Responses 3

Markdown supported · ⌘↵ to post

[Julian Neagu](https://hashnode.com/@julianneagulab)

[Jul 2](https://hashnode.com/posts/how-chat-gpt-understands-your-questions/6a44dd3b2915fb2210dca56b/comment/6a462a50203d6804882de1a0)

I like that you kept this simple. A lot of people think the model is searching the web every time. That one idea alone clears up a lot of confusion.
