korrents
Steve Klabnik

What Steve Klabnik thinks about LLMs

@steve-klabnik · 16 positions · On ppll ↗

Programmer and writer; co-wrote The Rust Programming Language and worked on Rust's documentation for years.

Steve Klabnik did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

8 dated positions, 2026, in their own words. Our reading of what Steve Klabnik has said — not written or endorsed by them.

  1. coding agents

    And the readability advantage for humans is even stronger for agents: the extra clarity of the text inline seems to (I haven't run real evals on this yet...) be more helpful and use less tokens and calls when looking at the actual call site.

    ↗Arguing about argumentssteveklabnik.com 2nd of 2 in this piece

  2. 8 months earlier
  3. The most important thing that you can do when working with an LLM is give it a way to quickly evaluate if it's doing the right thing, and if it isn't, point it in the right direction.

    ↗The most important thing when working with LLMssteveklabnik.com 1st of 3 in this piece

  4. Anthropic

    what's good for Claude is also probably good for humans working on your system.

    ↗The most important thing when working with LLMssteveklabnik.com 3rd of 3 in this piece

  5. 5 days earlier
  6. Anthropic

    Claude is going to try and figure out what you mean and do that. This is both the source of these tools' power and also the very thing that makes it hard to trust them.

    ↗Agentic development basicssteveklabnik.com 2nd of 3 in this piece

  7. Anthropic

    In the previous post, I said that you shouldn't be mean to Claude. I think it makes the LLM perform worse.

    ↗Agentic development basicssteveklabnik.com 3rd of 3 in this piece

  8. 7 days earlier
  9. I have a sneaking suspicion that the world has changed, and some old assumptions do not hold any longer.

    ↗How to think about Gas Townsteveklabnik.com 2nd of 2 in this piece

  10. 8 days earlier
  11. Becoming productive with LLMs is not actually easy, no matter what other people tell you.

    ↗Getting started with Claude for software developmentsteveklabnik.com 1st of 2 in this piece

  12. Anthropic

    I un-ironically believe that swearing at Claude makes it perform worse.

    ↗Getting started with Claude for software developmentsteveklabnik.com 2nd of 2 in this piece