korrents

Mario Zechner

@mario-zechner · 5 positions · 0 changes of mind

Austrian developer. Created the libGDX game framework, and more recently the pi coding agent, which moved with them to Earendil — Armin Ronacher's company — in April 2026. Writes at mariozechner.at.

Mario Zechner 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. 25 Mar 2026

    A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.

    An agent has no such learning ability. At least not out of the box. It will continue making the same errors over and over again. Depending on the training data it might also come up with glorious new interpolations of different errors.

    Thoughts on slowing the fuck downmariozechner.at

  2. 25 Mar 2026

    The human bottleneck is a safety property: remove it and small, individually harmless coding errors compound at a rate nobody feels until it is too late.

    With an orchestrated army of agents, there is no bottleneck, no human pain. These tiny little harmless booboos suddenly compound at a rate that's unsustainable. You have removed yourself from the loop, so you don't even know that all the innocent booboos have formed a monster of a codebase. You only feel the pain when it's too late.

    Thoughts on slowing the fuck downmariozechner.at

  3. 25 Mar 2026

    In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works.

    Worse, you realize that the gazillions of unit, snapshot, and e2e tests you had your clankers write are equally untrustworthy. The only thing that's still a reliable measure of "does this work" is manually testing the product.

    Thoughts on slowing the fuck downmariozechner.at

  4. 25 Mar 2026

    Two people with agents can reach enterprise-grade codebase complexity in weeks -- what took organisations years, and they at least adapted to it as it grew.

    And organizations have super high pain tolerance. But human-made enterprise codebases take years to get there. The organization slowly evolves along with the complexity in a demented kind of synergy and learns how to deal with it. With agents and a team of 2 humans, you can get to that complexity within weeks.

    Thoughts on slowing the fuck downmariozechner.at

  5. 25 Mar 2026

    Agentic code search has recall that falls as a codebase grows, so the agent does not find the code it needs -- and which search tool you give it barely matters.

    You can give it a Bash tool so it can ripgrep its way through the codebase. You can give it some queryable codebase index, an LSP server, a vector database. In the end it doesn't matter much. The bigger the codebase, the lower the recall. Low recall means that your agent will, in fact, not find all the code it needs to do a good job.

    Thoughts on slowing the fuck downmariozechner.at