korrents
Steve Klabnik

Steve Klabnik

@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.

  1. design

    they can be really concise, and beautiful to a certain kind of eye, but it also makes it really, really hard to know what all you can do with a function.

    ↗Arguing about argumentssteveklabnik.com 1st of 2 in this piece

  2. LLMscoding agentsdeveloper tools

    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

  3. 3 weeks earlier
  4. AI and jobs

    AI is here to stay, and it is dramatically changing how people work.

    ↗So, what happened to my Claude Code series?steveklabnik.com

  5. 7 weeks earlier
  6. designinfrastructure

    I think that this possibility is an important design property, and allows motivated users to meaningfully own their identity.

    ↗Too many words about DIDssteveklabnik.com 1st of 2 in this piece

  7. cryptocryptography

    A criticism of this boils down to "well, most users won't do that," and while that's true, I also think that's okay for most people, and that having the choice is more important than forcing every user to deal with their own key management.

    ↗Too many words about DIDssteveklabnik.com 2nd of 2 in this piece

  8. 4 days earlier
  9. AI alignmentcybersecurity

    it is unfortunate if these policies end up making it so that individuals like me can't make my software as robust as products from large organizations.

    ↗Compilers and AI 'cyber' defensesteveklabnik.com

  10. 5 months earlier
  11. LLMs

    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

  12. ideas vs execution

    the computer will do exactly what you say, but not what you mean.

    ↗The most important thing when working with LLMssteveklabnik.com 2nd of 3 in this piece

  13. LLMsAnthropic

    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

  14. 5 days earlier
  15. developer toolscode generation

    "AI does better on greenfield projects" is not exactly true, but there's enough truth to it that I think you should do a new project.

    ↗Agentic development basicssteveklabnik.com 1st of 3 in this piece

  16. LLMscoding agentsAnthropicdeveloper tools

    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

  17. LLMsAnthropic

    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

  18. 7 days earlier
  19. innovation

    And while rigor is a great value to have, when you're in an experimental mindset, relaxing rigor can be a valid strategy to move forward.

    ↗How to think about Gas Townsteveklabnik.com 1st of 2 in this piece

  20. LLMscoding agents

    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

  21. 8 days earlier
  22. LLMs

    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

  23. LLMsAI alignmentAnthropic

    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