korrents
Boris Cherny

What Boris Cherny thinks about LLMs

@boris-cherny · 35 positions · On ppll ↗

Creator of Claude Code at Anthropic.

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.

Filter LLMs · Newest first
Topic
All 35LLMs 11AI agents 4Anthropic 3coding agents 3design 3JavaScript 3prompt injection 2startups 2AI and jobs 1
17 more topics
AI and science 1ambition 1benchmarks 1chat interfaces 1code generation 1developer tools 1investing 1management 1neural networks 1open source 1optimism 1patience 1remote work 1scaling laws 1simplicity 1software performance 1software quality 1
Sort
NewestOldest

Only Boris Cherny on LLMs. See everyone on LLMs

11 dated positions, 2026, in their own words. Our reading of what Boris Cherny has said — not written or endorsed by them.

  1. Our readingPrompt work does not transfer across model generations: what you wrote three months ago for one model may be worth nothing to the next.

    Their wordsAnd the reason is every model is very different. So, something that you did for one model maybe 3 months ago, it just might not translate at all to the next model.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 3rd of 20 in this recording

  3. Our readingA frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.

    Their wordsAnd what's interesting is that the model is actually a little bit more intelligent without these prompts.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 4th of 20 in this recording

  5. 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

  7. Our readingA model is better thought of as a living creature with a personality you must get to know than as a component you specify.

    Their wordsAnd the model is not like that. It's um the way to think about it is almost like a like a living creature, like it's something more organic.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 8th of 20 in this recording

  9. Our readingProduct overhang: at every model generation the model can already do things no product yet lets it do, and the product is usually what is in the way.

    Their wordsBecause the model can do this at every given model generation, but there is often not a product that lets the model do this and lets it express this kind of ability to do this.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 10th of 20 in this recording

  11. Our readingThe way to find what a model can do is to hand it tasks slightly harder than you believe it can handle.

    Their wordsOne is you should give the model slightly harder tasks than what you think it can do.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 11th of 20 in this recording

  13. Our readingThere are dozens or hundreds of things today's models can already do that nobody has discovered yet, and they are found by playing rather than by planning.

    Their wordsAnd my hypothesis is there's probably dozens, hundreds of opportunities like this with the models of today that no one has yet realized.

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 13th of 20 in this recording

  15. Our readingThe skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong.

    Anthropicchat interfaces

    Their wordsI think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard. And then how do you make it possible for Claude to verify its work along the way? And the verification I think is probably the single most important thing that people do not get right

    ↗Boris Cherny: We Cut 80% of Claude Code's Promptyoutube.com 14th of 20 in this recording

  17. Our readingWorking with models has stopped being a theoretical science and become an empirical one, so your priors from computer science class are a hindrance.

    Their wordsAnd it's really about being empirical. So forget all of the things that you learned about past models. Forget everything that you've learned about computer science theory in class. Look at the model, try to do a task, see where it struggles, and then based on that adjust. So it's just like very much become it's not a theoretical science, it's become an empirical science.

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

  18. 5 months earlier

  19. Our readingA migration must be finished once it is started, because a half-migrated codebase confuses models as much as it confuses people.

    Their wordsalways make sure that when you start a migration, you finish the migration.

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

  20. 7 days earlier

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

    Anthropicstartups

    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