Since officially joining Anthropic on May 19th this year, Andrej Karpathy's activity in the open-source community has dropped significantly, and he is also posting less on the X platform recently. He had an argument with netizens on X these days, complaining that the recommendation algorithm drives traffic through conflicts, which worsens the community atmosphere. Elon Musk also admitted: Indeed, we need to make a thorough improvement. Recently, someone said, "I have a friend who got the CLAUDE.md file that Andrej Karpathy actually uses." CLAUDE.md is a project-level instruction document specifically written for Claude AI. The file exists because large language models make some predictable mistakes when writing code. These mistakes do not occur randomly; they are always the same kind of problems, appearing over and over again. The file states: "These are not suggestions. These are rules. Follow them, and the code you produce won't need to be rewritten. Ignore them, and the code you produce may seem great, but it will cause problems in the production environment." Before writing any code, the rules instruct to read the file you are about to modify carefully, check how similar functions are implemented in the project, and check the imports at the top of the file.