korrents
Simon Willison

What Simon Willison thinks about coding agents

@simon-willison · 29 positions · 0 changes of mind

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

Everything they publish, on ppll ↗

Simon Willison 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, 2025 to 2026, in their own words. Our reading of what Simon Willison has said — not written or endorsed by them.

  1. Our readingAuto-mode does not yet convincingly fix prompt-injection risk for coding agents.

    Their wordsI REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet

    ↗@simonw on Xx.com

    prompt injection

    Interesting
  2. 5 months earlier

  3. Our readingTest-driven development matters more with coding agents than it ever did with people, because its real effect is stopping the agent writing more code than the task needs.

    Their wordsthe key thing about TDD is that it means that the agents won't write more than they need to.

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 3rd of 18 in this recording

    Interesting

  5. Our readingWriting code with a coding agent and no tests at all is indefensible, because the old objection to testing — that it is extra work you then have to maintain — no longer applies.

    Their wordsI think I see people who are writing code with coding agents and they're not writing any tests at all. That's a terrible idea.

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 4th of 18 in this recording

    Interesting

  7. Our readingWorking with coding agents is exhausting rather than deskilling, and that exhaustion — not the technology — is what limits how many projects one engineer can run at once.

    Their wordsI think that might be what saves us. I think the fact that no, you can't have one engineer and have him do a thousand projects because after three hours of that he's going to literally pass out in a corner.

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 15th of 18 in this recording

    Interesting
  8. 3 months earlier

  9. Our readingMCP may turn out to be a one-year wonder, because coding agents that can run arbitrary shell commands make Bash the best general-purpose tool interface.

    Their wordsThe reason I think MCP may be a one-year wonder is the stratospheric growth of coding agents. It appears that the best possible tool for any situation is Bash—if your agent can run arbitrary shell commands, it can do anything that can be done by typing commands into a terminal.

    ↗2025: The year in LLMssimonwillison.net

    MCP

    Interesting

  11. Our readingRunning coding agents without approval prompts is a normalization-of-deviance risk: the fact that it has not caused a disaster yet is itself the problem.

    Their wordsI run in YOLO mode all the time, despite being deeply aware of the risks involved. It hasn’t burned me yet... ... and that’s the problem.

    ↗2025: The year in LLMssimonwillison.net

    Interesting