What Mario Zechner thinks about coding agents
Austrian developer who 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.
Everything they publish, on ppll ↗
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.
6 dated positions, 2026, in their own words. Our reading of what Mario Zechner has said — not written or endorsed by them.
-
Our readingCodex team's new features likely do not work well with models not trained on that mechanism
Their wordstheir new stuff is very interesting, but likely doesn't work amazingly well with models not trained on this mechanism.
- 5 months earlier
-
Their wordsAn 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.
-
Their wordsWith 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.
-
Their wordsWorse, 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.
-
Their wordsAnd 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.
-
Their wordsYou 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.