korrents
Simon Willison

What Simon Willison thinks about design

@simon-willison · 41 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.

10 dated positions, 2024 to 2026, in their own words. Our reading of what Simon Willison has said — not written or endorsed by them.

10 positions so far — this page is not yet offered to search engines.

  1. I think that as a form of intellectual personal protective equipment you should adopt the rule that any specific turn of phrase an LLM suggests is off limits.

    How To Write With An LLMsimonwillison.net

    LLMs

  2. 5 days earlier
  3. Frustratingly, the actual code it ran and exact details of what it did weren’t visible to me in the ChatGPT UI. I see this lack of transparency is an anti-feature.

    Generating running routes with GPT-6 Astra and ChatGPT Worksimonwillison.net

    OpenAI

  4. 8 days earlier
  5. It looks to me like OpenAI’s sandbox for this agent suffered from the (quite naïve) assumption that GET requests cannot be used to update data. That’s certainly how the web is supposed to work, but clearly there are applications that don’t hold to that contract.

    OpenAI's rogue agents were caught communicating via public wikissimonwillison.net

    OpenAI

  6. 1 day earlier
  7. OpenAI may have vanquished one of the ongoing challenges with long context processing.

    GPT‑6 Astrasimonwillison.net

    OpenAI

  8. 2 days earlier
  9. its connection to how good the models were at other tasks didn’t seem to hold as strongly as it did back in 2025

    Claude Fable 5.1 made me a really nice animated pelicansimonwillison.net

    benchmarks

  10. 5 months earlier
  11. just cuz the test suite passes doesn't mean that the web server will boot. You know, there's there's always a chance that when you actually try in the real world, something's not going to work.

    Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 5th of 18 in this recording

    software quality

  12. And what you can do if you've got one of these conformance suites is you can give it to a a good agent and say, "Write code until this test suite passes." And it kind of will.

    Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 6th of 18 in this recording

    software quality

  13. The problem with language models is they're incredibly gullible by design. Like, language models do exactly what you tell them to do, and they will believe almost anything that you say to them.

    Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 9th of 18 in this recording

    LLMs

  14. Problem is, you can solve SQL injection by parameterizing your queries. You can't do that with LLMs.

    Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com 10th of 18 in this recording

    LLMsprompt injection

  15. 15 months earlier
  16. There’s still plenty to worry about with respect to the environmental impact of the great AI datacenter buildout, but a lot of the concerns over the energy cost of individual prompts are no longer credible.

    Things we learned about LLMs in 2024simonwillison.net

    LLMsdata centersenergy