korrents
Boris Cherny

What Boris Cherny thinks about design

@boris-cherny · 25 positions · 0 changes of mind

Creator of Claude Code at Anthropic.

Everything they publish, on ppll ↗

Boris Cherny 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 Boris Cherny has said — not written or endorsed by them.

8 positions so far — this page is not yet offered to search engines.

  1. Our readingEvery six months you should delete your whole AI configuration — instructions, skills and hooks — and find out how much of it the model never needed.

    Their wordsfor people that aren't building agentic products, but you're using Claude code, every 6 months delete your Claude MD. Delete your skills. Delete your hooks.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 5th of 20 in this recording

    Anthropic

    Interesting

  3. Our readingYou cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance.

    Their wordsAnd you don't want to guess what's the instruction that the model needs because you might not predict it correctly. The thing that you want to do is you want to run it.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 6th of 20 in this recording

    Interesting

  5. Our readingBuilding on a model is unlike any previous software engineering, because the thing you are building on cannot be designed up front.

    Their wordsI I think this is sort of the crazy thing about building on models. It's just so different than all the engineering that I've ever done. Like in the past when you built on systems, you built these like big beautiful systems and you really think about the system design up front. You have like a big suite of unit tests. You think about everything and you know, like a re-architecture is a big project.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 7th of 20 in this recording

    software quality

    Interesting

  7. Our readingEvals are not the durable asset people think they are: one survives about one to three model generations before it saturates and has to be thrown away.

    Their wordsI think evals, they outlive the harness a little bit, but not by that much. Like an eval might live for maybe one, two, three model generations, but nowadays the you know, we're on the exponential. The model is improving so quickly, very often we just saturate the eval, and then we have to throw it away, and we have to come up with a new eval.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 9th of 20 in this recording

    Interesting

  9. Our readingCoding is solved for the kind of coding he does, and not for everyone: deep systems work, distributed systems and pixel-level UI checking still defeat the model.

    Their wordsSo coding is solved for the kind of coding that I do. It's not solved for everyone. You know, there's still code bases that are like super deep systems code bases where quad still struggles.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 19th of 20 in this recording

    Interesting
  10. 5 months earlier

  11. Our readingWorking prototypes have replaced product requirement documents.

    Their wordsThere’s just no way we could have shipped this if we started with static mocks and Figma or if we started with a PRD.

    ↗Building Claude Code with Boris Cherny — The Pragmatic Engineernewsletter.pragmaticengineer.com

    Interesting

  13. Our readingThe scarce skill is now context switching across parallel agents, not sustained deep work.

    Their wordsIt’s not so much about deep work, it’s about how good I am at context switching and jumping across multiple different contexts very quickly.

    ↗Building Claude Code with Boris Cherny — The Pragmatic Engineernewsletter.pragmaticengineer.com

    Interesting
  14. 7 days earlier

  15. Our readingBuild for the model six months from now, not the model of today.

    Their wordsAt Anthropic, we don't build for the model of today, we build for the model of six months from now. And that's still my advice to founders that are building on LLMs.

    ↗Y Combinator, quoting Boris Cherny on the Lightcone Podcastx.com

    LLMsAnthropicstartups

    Interesting