What Simon Willison thinks about design
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.
-
Their wordsI 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.
- 5 days earlier
-
Our readingHiding the code and exact details of what an agent ran from the ChatGPT UI is an anti-feature.
Their wordsFrustratingly, 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
- 8 days earlier
-
Their wordsIt 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
- 1 day earlier
-
Their wordsOpenAI may have vanquished one of the ongoing challenges with long context processing.
- 2 days earlier
-
Our readingThe pelican-drawing benchmark's correlation with genuine model capability has weakened since 2025.
Their wordsits 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
- 5 months earlier
-
Their wordsjust 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
-
Their wordsAnd 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
-
Their wordsThe 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
-
Their wordsProblem 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
- 15 months earlier
-
Their wordsThere’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.