Andrej Karpathy on X: "Continuing the journey of optimal LLM-assisted coding experience. In particular, I find that instead of narrowing in on a perfect one thing my usage is increasingly diversifying across a few workflows that I "stitch up" the pros/cons of: Personally the bread & butter (~75%?) o
Quick Answer
Andrej Karpathy emphasizes a diversified approach to LLM-assisted coding, favoring hands-on code writing for task specification over text prompts.
Quick Take
Andrej Karpathy emphasizes a diversified approach to LLM-assisted coding, favoring hands-on code writing for task specification over text prompts. He utilizes Claude Code and Codex for larger functionalities but finds them less effective for teaching.
Key Points
- Karpathy writes code directly to communicate task specifications effectively.
- He uses Claude Code and Codex for larger functionality prompts.
- Teaching through LLMs like CC proved ineffective for Karpathy.
- Hands-on coding is preferred for high bandwidth communication.
- Approximately 75% of his workflow involves direct coding.
Article Excerpt
From source RSS / original summaryThis is because I find that writing concrete chunks of code/comments myself and in the right part of the code is a high bandwidth way of communicating "task specification" to the LLM, i. e. it's primarily about task specification bits - it takes too many bits and too much latency to communicate what I want in text, and it's faster to just demonstrate it in the code and in the right place.
Next layer up is Claude Code / Codex / etc, running on the side of Cursor, which I go to for larger chunks of functionality that are also fairly easy to specify in a prompt. I also tried CC to teach me things alongside the code it was writing but that didn't work at all - it really wants to just write code a lot more than it wants to explain anything along the way.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from WebSearch (Tavily)
See more →WSJ: OpenAI is considering deep price reductions as competition ...
OpenAI is contemplating significant price cuts in response to competitive pressure from Anthropic, particularly due to the success of Claude Code in developer and coding workflows. This shift could affect pricing strategies in the AI market as companies vie for dominance in coding solutions.