# Has anyone tried the Karpathy CLAUDE.md rules? (97.8k stars)

**URL:** <https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109>\
**Category:** AI Chat/Discussions\
**Tags:** claude\
**Created:** [29 April 2026 15:44 UTC](https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109 "2026-04-29T15:44:42Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![usernametakenaaaa](https://forum.devtalk.com/user_avatar/forum.devtalk.com/usernametakenaaaa/32/8037_2.png) [@usernametakenaaaa](https://forum.devtalk.com/u/usernametakenaaaa)\
**Post date:** [30 April 2026 01:16 UTC](https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109/2 "2026-04-30T01:16:04Z")

</div>

I basically came up with something very similar on my own. These kind of commands definitely help but you need to adapt them to your project and to the AI models you use.  
Especially ideas like “investigate instead of assuming” - to a human it sounds easy and models do make those errors and they cause catastrophic issues .. but telling a model to not assume is quite fruitless.  
A rule against Abstractions is among the most helpful rules I use.

---

_[View the full topic](https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109)._
