korrents
Peter Steinberger

What Peter Steinberger thinks about coding agents

@peter-steinberger · 51 positions · 0 changes of mind

Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.

Everything they publish, on ppll ↗

Peter Steinberger 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.

11 dated positions, 2025 to 2026, in their own words. Our reading of what Peter Steinberger has said — not written or endorsed by them.

  1. Our readingWith agents a new feature is one prompt away, which means the whole cost of a feature has moved to what happens after you ship it.

    Their wordsYou know features are the fun part. A new feature is is just a prompt away. The real cost comes after every feature we shipped of course with a configuration option because we didn't want to break everyone's setup.

    ↗Peter Steinberger: "Fun Is Velocity"youtube.com 5th of 22 in this recording

    Interesting

  3. Our readingClearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does.

    Their wordsAnd these days it's more like my sessions are topics. clearing the session sometimes even a disadvantage because there's so much information in there that helps the agent.

    ↗Peter Steinberger: "Fun Is Velocity"youtube.com 11th of 22 in this recording

    Interesting

  5. Our readingBringing a colleague a feature idea rather than a built, screenshotted prototype now wastes everyone's time, because most ideas die the moment you try to build them.

    Their wordsAt the same time, at work, if you come to me and you you tell me this feature idea, I'm going to get mad at you. Like, it's so easy that you just discuss the feature idea with an agent, you build it, you make screenshots, you let me play with it.

    ↗Peter Steinberger: "Fun Is Velocity"youtube.com 12th of 22 in this recording

    Interesting

  7. Our readingReviewing agent-written code is risk management rather than reading: how long the change took and how big it is tell you when to look closely.

    Their wordsPart of it is just like you develop a little bit of a feeling how long something should take. So if I do a small tweak that should like change how dragging works and it takes three hours, I know something's wrong. I'll look closely. But otherwise, part of code review is simply like observing, looking how big it changes and trusting your gut.

    ↗Peter Steinberger: "Fun Is Velocity"youtube.com 14th of 22 in this recording

    Interesting

  9. Our readingThe binding constraint on agent work is machines, not models: a cloud session is easy for web work and almost every tool fails the moment the job needs macOS.

    Their wordsNow, if I do web stuff, it's easy to create a cloud session. If I do like something that requires Mac OS, that's already where like 99% of the tools fail me.

    ↗Peter Steinberger: "Fun Is Velocity"youtube.com 17th of 22 in this recording

    Interesting
  10. 6 months earlier

  11. Our readingWorking with coding agents is a skill you learn like an instrument; judging the tools after one try is like calling a piano bad after one go.

    Their wordsIt's the same way as you have to play with a guitar before you can make good music. It's, it's not, oh, I, I touch it once and it just flows off. It, it's a, it's a, a skill that you have to learn like any other skill.

    ↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 10th of 30 in this recording

    Interesting

  13. Our readingRefactors are cheap now, so he just does them, even when they break other people's open pull requests.

    Their wordsMany times, I just do the refactor because refactors are cheap now. Even though you might break some other PRs, nothing really matters anymore.

    ↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 11th of 30 in this recording

    Interesting

  15. Our readingHe builds the code base to be easy for an agent to navigate, not to be perfect for himself, down to keeping the names the model picks.

    Their wordsI- i- like, we are in a stage where I'm not building the code base to be perfect for me, but I wanna build a code base that is very easy for an agent to navigate.

    ↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 12th of 30 in this recording

    Interesting

  17. Our readingOpus is the silly but funny coworker you keep around; Codex is the weirdo in the corner who reliably gets things done, and no model wins on every axis.

    Their wordsSome other comparison is like, Opus is like the coworker that is a little silly sometimes, but it's really funny and you keep him around. And Codex is like the, the weirdo in the corner that you don't wanna talk to, but is reliable and gets shit done.

    ↗OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491youtube.com 15th of 30 in this recording

    Interesting
  18. 6 months earlier

  19. Our readingTests written by a model in the same context as the change are what find the bugs; the automated tests left behind are the lesser product.

    Their wordsBigger changes always get tests. Automated ones usually aren’t great, but the model almost always finds issues when you ask it to write tests IN THE SAME CONTEXT. Context is precious, don’t waste it.

    ↗My Current AI Dev Workflowsteipete.me

    Interesting

  21. Our readingBackground agents do not work for real development, because steering a model as it drifts is the job, and you cannot steer what you are not watching.

    Their wordsStill don’t see how this could be moved to background agents. I steer the models a lot as I notice them drifting off - that’s much harder if they run in the background.

    ↗My Current AI Dev Workflowsteipete.me

    Interesting