@Soranlan: https://x.com/nobel_824/status/2057643942980751527/video/1… The craziest part about this thing is that it's not even code. A 65-line plain text file, straight to #1 on GitHub Trending with 100k stars. Not a library, not a...
Summary
A 65-line plain text file called CLAUDE.md by OpenAI co-founder Karpathy reached 100k stars on GitHub, becoming the top trending repository. It's not code or a framework, but a set of operational instructions on how to collaborate efficiently with AI in writing code, clarifying the division of labor between humans and machines to better leverage tools like Claude Code.
View Cached Full Text
Cached at: 05/24/26, 08:36 PM
https://x.com/nobel_824/status/2057643942980751527/video/1…
The most absurd thing about this is —
it’s not even code.
65 lines of plain text, straight to #1 on GitHub Trending, 100,000 stars. Not a library, not an app, not a framework — just a “how to code with AI” instruction manual. Once again, Karpathy grabbed the entire community’s attention with something incredibly minimal.
What’s really valuable isn’t how to configure Claude Code — it’s how he lays out the boundary between human and AI: how to make the model less stupid, how to keep context clean, how to break fuzzy tasks into granular steps AI can execute. Most people can’t use Claude Code well — it’s not the model’s fault, it’s that they feed it badly from the start.
65 lines earning 100,000 stars proves the industry isn’t short of boats anymore — it’s short of people who know how to sail.
tatsuki (@nobel_824): OpenAI co-founder Karpathy’s CLAUDE.md is dominating #1 on GitHub Trending. It’s not a library or an app — just a 65-line text file. One file that distills Karpathy’s coding observations, now with over 100,000 stars total. Let me explain the four principles written there.
Similar Articles
@XAMTO_AI: An OpenAI founding member threw a CLAUDE.md onto GitHub, gaining 44k stars in a week, total stars hit 100k—even Stack Overflow didn't get that treatment. He observed that the biggest problem with AI programming is not that it can't work, but that it "loves to improvise": ask it to fix a ...
OpenAI founding member releases CLAUDE.md file, uses four principles to constrain AI coding assistant from over-improvising and complicating things, gaining 44k GitHub stars in a week.
@NFTCPS: Karpathy's CLAUDE.md tops GitHub Trending with 220k stars, but I bet you haven't read it. Just 65 lines. It boosts AI code generation accuracy from 65% to 94%. You know what most people are doing? Stacking prompts, buying courses, researching 'the strongest...'
Introduces (nominally) Karpathy's CLAUDE.md file, just 65 lines and 4 rules, claiming to boost AI code generation accuracy from 65% to 94%. Actually points to the entropyvortex/meta-llm-charter repository, which is an engineering charter for LLM coding agents, containing 11 rules and a zero-pause execution layer.
@InduTripat82427: OpenAI co-founder Karpathy's CLAUDE.md is dominating the #1 spot in GitHub trends. Its contents are neither a library n…
Andrej Karpathy's CLAUDE.md file, a 65-line text file outlining coding principles, has become the #1 trending repository on GitHub with over 100k stars.
@FakeMaidenMaker: If you really want to understand how the underlying of AI Agents like Claude Code is built, this open-source project writes one from scratch for you to see. GitHub has garnered 66.5K Stars, and also made it to the Trendshift hot list. The intelligence of an Agent comes from the model itself; what you can do is not "building intelligence"...
An open-source project teaches you to build a simplified version of Claude Code from scratch, thoroughly explaining the harness engineering of AI Agents. It has received 66.5K Stars.
@akshay_pachaar: A single 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file just hit 192k GitHub stars. (derived from Karpathy's coding rules) Andrej Karpathy obse…
A single CLAUDE.md file that provides structured behavioral guidelines for Claude Code, derived from Andrej Karpathy's observations on common LLM coding pitfalls, has gained 192k GitHub stars. It aims to prevent over-engineering, reduce wrong assumptions, and enforce simplicity in AI-generated code.