xiji2646-netizen

xiji2646-netizen

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

There’s a GitHub repo at forrestchang/andrej-karpathy-skills that’s sitting at 97.8k stars. It’s a single CLAUDE.md file with four behavioral rules for Claude Code, derived from Andrej Karpathy’s observations about LLM coding failure modes.

The four rules:

  1. Think Before Coding — ask instead of assuming

  2. Simplicity First — no abstractions nobody asked for

  3. Surgical Changes — touch only what you must, every diff line traces to the request

  4. Goal-Driven Execution — define success criteria, loop until met

I’ve been using it for a few weeks. The one that made the biggest difference for me is Surgical Changes. Before, I’d ask for a bug fix and get a 40-line diff with type hints, reformatted quotes, and renamed variables mixed in with the actual fix. Now the diff is clean.

Has anyone else tried it? Curious whether the “simplicity first” rule causes problems in codebases that genuinely need abstractions — I’ve had to work around it a couple of times.

Installation is one command:


/plugin marketplace add forrestchang/andrej-karpathy-skills

/plugin install andrej-karpathy-skills@karpathy-skills

Most Liked

usernametakenaaaa

usernametakenaaaa

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.

Where Next?

Popular Ai topics Top

AstonJ
I have a feeling we’re going to see a lot of threads about DeepSeek, so have put up a portal for it :003:
New
AstonJ
Curious what kind of results others are getting, I think actually prefer the 7B model to the 32B model, not only is it faster but the qua...
New
apoorv-2204
I’m reaching out to all software engineers, especially senior developers — I really want to hear your thoughts. I’ve always loved buildi...
New
kammy
Hi everyone! The other day I was having a debate with my friends about whether or not the top LLM models are “good at design.” I’d love ...
New
xiji2646-netizen
I’ve been following Seedance 2.0 since ByteDance dropped it in February, and after a few weeks of testing through third-party APIs, I wan...
New
xiji2646-netizen
Google just dropped a significant Deep Research upgrade: collaborative planning, multi-tool orchestration (MCP servers, Code Execution, F...
New
xiji2646-netizen
Alibaba just opened public API access for HappyHorse 1.0, the model currently ranked #1 on Video Arena’s blind tests. What caught my att...
New
xiji2646-netizen
Been using Claude Code on Max for a few weeks and kept running into rate limits by early afternoon. Same tasks as colleagues who weren’t ...
New
xiji2646-netizen
Anthropic shipped something called Dreaming for Managed Agents this week. It’s a scheduled background process that runs between sessions ...
New
LatentLogic
I recently integrated Seedance 2.5 into one of my own projects. The basic API flow is simple: create a task, get the task ID, and poll un...
New

Other popular topics Top

dasdom
No chair. I have a standing desk. This post was split into a dedicated thread from our thread about chairs :slight_smile:
New
AstonJ
In case anyone else is wondering why Ruby 3 doesn’t show when you do asdf list-all ruby :man_facepalming: do this first: asdf plugin-upd...
New
AstonJ
We’ve talked about his book briefly here but it is quickly becoming obsolete - so he’s decided to create a series of 7 podcasts, the firs...
New
PragmaticBookshelf
Author Spotlight Jamis Buck @jamis This month, we have the pleasure of spotlighting author Jamis Buck, who has written Mazes for Prog...
New
DevotionGeo
I have always used antique keyboards like Cherry MX 1800 or Cherry MX 8100 and almost always have modified the switches in some way, like...
New
NewsBot
Node.js v22.14.0 has been released. Link: Release 2025-02-11, Version 22.14.0 'Jod' (LTS), @aduh95 · nodejs/node · GitHub
New
PragmaticBookshelf
Fight complexity and reclaim the original spirit of agility by learning to simplify how you develop software. The result: a more humane a...
New
Fl4m3Ph03n1x
Background Lately I am in a quest to find a good quality TTS ai generation tool to run locally in order to create audio for some videos I...
New
xiji2646-netizen
Woke up to this today: Claude Code’s complete source code exposed via npm source map. Not a snippet. All 512,000 lines. 1,900 TypeScript ...
New
xiji2646-netizen
There’s a GitHub repo at forrestchang/andrej-karpathy-skills that’s sitting at 97.8k stars. It’s a single CLAUDE.md file with four behavi...
New