korrents
David Heinemeier Hansson

What David Heinemeier Hansson thinks about coding agents

@dhh · 154 positions · 10 changes of mind

Creator of Ruby on Rails, CTO of 37signals, and creator of Omarchy.

Everything they publish, on ppll ↗

David Heinemeier Hansson 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.

22 dated positions, 2024 to 2026, in their own words. Our reading of what David Heinemeier Hansson has said — not written or endorsed by them.

Our readingThis is the record with a turn in it: two positions holding that writing the code was not the part to hand over were abandoned in April 2026, on the account that the facts changed rather than the opinion. What stands now is that the gains are real but go to whoever works with the agent directly.

Their wordsThe revelation I've had working on Omarchy the last three months is that to get that magical 10X, 100X, in a few rare cases, 1000X productivity boost, you have to interact with the agents directly, and you cannot intermediate that bandwidth with another human because it's simply too slow.

The very large productivity gains from agents require working with them directly; putting another human in between is too slow to preserve the gain.

  1. Our readingThe release of Opus 4.5 in November 2025 was the dividing line, because it was the first time an agent produced work uncannily close to what its user would have written themselves.

    Their wordsThen we get to November 24th, 2025. Opus 4.5, to me, was the dividing line, where suddenly... I didn't even try it on the 24th. I think I tried it on the 26th. I give it a couple of tasks, and I realize that the quality of the output is uncannily close to what I would've written.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 2nd of 41 in this recording

    Interesting

  3. Our readingThe very large productivity gains from agents require working with them directly; putting another human in between is too slow to preserve the gain.

    Their wordsThe revelation I've had working on Omarchy the last three months is that to get that magical 10X, 100X, in a few rare cases, 1000X productivity boost, you have to interact with the agents directly, and you cannot intermediate that bandwidth with another human because it's simply too slow.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 5th of 41 in this recording

    Omarchy

    Interesting

  5. Our readingMost organisations are bottlenecked on ideas, vision and taste rather than on implementation, so making code cheap does not make them productive.

    Their wordsThe other thing I'd say is that most organizations don't know what they want. They don't know how to make it better. They're not bottlenecked on implementation. They're bottlenecked on ideas. They're bottlenecked on vision. They're bottlenecked on taste. And if you don't have those element in excess of your implementational capacity, it doesn't help. So you can make a lot of shitty ideas come true, then what?

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 6th of 41 in this recording

    taste

    Interesting

  7. Our readingSoftware lock-in is breaking, because rewriting just the 5% of an application you personally use is now within one person's reach.

    Their wordsAnd maybe you won't get to 100% coverage, but this is the old joke about Microsoft Office. "I only use 5%." Yeah, well, we all use a different 5%. Well, what if we all just build our own 5%? What if I just took the functionality that I need and just did that? That is a completely different challenge and one agents are incredibly capable of doing right now, today, and I've done it a lot of times over.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 7th of 41 in this recording

    Microsoft

    Interesting

  9. Our readingAgent-written pull requests already outclass those of the median human contributor to an open source project.

    Their wordsBut it actually means that if you take the median programmer and their pull requests towards an average open source project, they're already getting outclassed by agents. I would rather get an agent-written pull request to one of my projects than I'd get one written by a human, and it's not just because the quality's better. It's also because I feel a lot less bad if I just reject it.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 8th of 41 in this recording

    open source

    Interesting

  11. Our readingA maintainer no longer needs to read every pull request; agents can sort the chaff and leave only the decisions worth a human.

    Their wordsI'm not reviewing every pull request anymore. I haven't been reviewing them for quite some time now.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 10th of 41 in this recording

    Interesting

  13. Our readingOverly prescriptive instructions make a coding agent worse, for the same reason a micromanaging boss makes a programmer worse.

    Their wordsit was actually being damaged by overly prescriptive humans. And any programmer who's had a pointy-haired boss knows exactly what that is like. When the boss walks into the room, doesn't know anything, starts telling you how to program, how to code. What do you do? You sulk. You write shittier code if you're mandated to do things that are against your better judgment. Why would an agent not be the same?

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 14th of 41 in this recording

    Interesting

  15. Our readingYou cannot know what a program should do until you play with it, so in the agentic age you should be as vague as you can up front and then interact with what appears.

    Their wordsNo one was happy. Because no one knows what they want until they receive it. You don't know what a program should do until you play with it. So in the agentic age, you should resist the temptation to be overly specific upfront. Be as vague as you can to manifest something, then interact with the something. The way you arrive at good software is you write a little bit of software, and then you try to use it. It is in the process of using software that you discover what you really want.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 15th of 41 in this recording

    Interesting

  17. Our readingThere is no accumulated advantage in agentic coding: someone who ignored the whole of the past year could catch up to the frontier in two weeks.

    Their wordsThere's not any accumulation, which is in some ways a great relief.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 20th of 41 in this recording

    Interesting

  19. Our readingIn most domains agents are now better than humans at finding bugs.

    Their wordsAnd this was with models we had six months ago. At this point, 100% in the majority of domains we work in today, agents are better at finding bugs.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 23rd of 41 in this recording

    Interesting
  20. 3 months earlier

  21. Our readingAI coding agents advance open source's founding goal by letting far more people modify software, so barring AI-assisted contributions protects a guild rather than the mission.

    Their wordsAgents aren't perfect, slop is a problem, but giving more people the power to enjoy malleable computers is undoubtedly a huge win for the founding vision of open source.

    ↗Let the agents democratize open sourceworld.hey.com

    open source

    Interesting
  22. 8 weeks earlier

  23. Our readingRails is having a renaissance because it is one of the most token-efficient ways to build a web app, which suits agents, for as long as that lasts.

    Their wordsI think in some ways Ruby Rails is having a little bit of a renaissance now that it is one of the most token efficient ways of building web apps. It's ideally suited for the agent workflows we're dealing with now. We'll see how long that lasts.

    ↗DHH’s new way of writing codeyoutube.com 1st of 20 in this recording

    Ruby

    Interesting

  25. Our readingHis opinion of AI never changed; the circumstances and the facts did, when agent harnesses and Opus 4.5 made the tools good enough.

    Their wordsI don't actually think my opinions have changed. What have changed is the circumstances and the facts

    ↗DHH’s new way of writing codeyoutube.com 6th of 20 in this recording

    Interesting

  27. Our reading · no longer heldAI is welcome as a better search engine and a pair programmer that does not drive, but writing the code itself is not something to hand over to it.

    No longer holdsI will now start any project I'm starting with. I'm starting agent first and that's a massive shift

    SaidWhat I failed to realize at the time was that running a bunch of agents feels less like being a project manager for agents and more like stepping into this super mech suit where suddenly I don't just have two arms.

    ↗DHH’s new way of writing codeyoutube.com 7th of 20 in this recording

    Interesting

  29. Our readingAnthropic pulling Claude subscriptions from third-party harnesses like OpenCode is a mistake: playing a single match in a game of many rounds.

    Their wordsSo then they started thinking a little bit in that like the game is single match instead of thinking it's multiple rounds and yanked their subscription from open code.

    ↗DHH’s new way of writing codeyoutube.com 9th of 20 in this recording

    Anthropic

    Interesting

  31. Our readingThe bulk of agent acceleration is accruing to senior programmers, because judging whether agent output can ship is what made them senior.

    Their wordsthe most successful and applicable agent acceleration that I've seen at 37 signal has been from the most senior people the people who are able to validate whether what the agent produces is suitable to be deployed to millions of people.

    ↗DHH’s new way of writing codeyoutube.com 11th of 20 in this recording

    Interesting

  33. Our reading · no longer heldThe joy of a programmer is to type the code himself; promoting yourself out of that makes you a project manager of a murder of AI crows.

    No longer holdsI have been hyper accelerated as a programmer. It's a different kind of programmer, but it still has the same affinity to aesthetics, at least when I'm producing Ruby code.

    Saidthat's the biggest revelation actually more than even the capacity of the agents is my enjoyment running them.

    ↗DHH’s new way of writing codeyoutube.com 13th of 20 in this recording

    Ruby

    Interesting

  35. Our readingThe pie of software work is exploding, not growing: with the cost of exploring a hunch down a thousandfold, projects nobody would have contemplated get done.

    Their wordswe're getting ambitions we would never have looked at before because suddenly the cost of exploring a hunch has just dropped by a thousandfold.

    ↗DHH’s new way of writing codeyoutube.com 14th of 20 in this recording

    Interesting
  36. 9 months earlier

  37. Our readingAI is welcome as a better search engine and a pair programmer that does not drive, but writing the code itself is not something to hand over to it.

    Their wordsI love chiseling my code and the way I use AI is in a separate window. I don't let it drive my code. I've tried that. I've tried the cursors and the wind surfaces and I don't enjoy that way of writing. And one of the reasons I don't enjoy that way of writing is I can literally feel competence draining out of my fingers.

    ↗DHH: Future of Programming, AI, Ruby on Rails, Productivity & Parenting | Lex Fridman Podcast #474youtube.com 9th of 36 in this recording

    Interesting

  39. Our readingThe joy of a programmer is to type the code himself; promoting yourself out of that makes you a project manager of a murder of AI crows.

    Their wordsThe joy of a programmer, of me as a programmer, is to type the code myself. If I elevate myself, if I promote myself out of programming, I turn myself into a project manager. A project manager of a murder of AI crows as I wrote the other day.

    ↗DHH: Future of Programming, AI, Ruby on Rails, Productivity & Parenting | Lex Fridman Podcast #474youtube.com 10th of 36 in this recording

    Interesting
  40. 3 months earlier

  41. Our readingHowever capable AI coding tools become, the industry will still need junior programmers, because someone must be able to vet what the machine produces.

    Their wordsHowever good AI gets, we're always going to need people who know the ins and outs of what the machine comes up with.

    ↗We'll always need junior programmersworld.hey.com

    AI and jobs

    Interesting
  42. 7 months earlier

  43. Our readingAI is welcome as a better search engine and a pair programmer that does not drive, but writing the code itself is not something to hand over to it.

    Their wordsI enjoy it even almost like as a sort of pair programmer AI pair programmer who doesn't drive who's just there to give suggestions to know the API to do all these other things but the second it starts wanting to autocomplete my code I'm like yeah I'm out bro

    ↗DHH Is Right About Everythingyoutube.com 8th of 8 in this recording

    Interesting