korrents

← People and their mental models

Simon Willison's mental models

4 claims Simon Willison made fit 4 mental models. Most often: Design is how it works, Incentives, Margin of safety. Everything they said here.

Models we see in what they say

Our reading: their claim applies the idea without naming it. The claim is theirs; filing it here is ours.

Design is how it works

Judge a design by what it does for the person using it, not only by how it looks.

Used by 26 others

The addition of a visual preview and the ability to type or paste things makes interacting with a coding agent much more powerful.

  1. Simon Willison Co-creator of Django and creator of Datasette The addition of the visual preview, plus being able to type or paste things in via the keyboard when I need to communicate something that doesn’t work vocally, makes this a much more powerful way of interacting with a coding agent. A new feature for my blog, built using my voicesimonwillison.net · 9 Oct 2026
    Their wordsThe addition of the visual preview, plus being able to type or paste things in via the keyboard when I need to communicate something that doesn’t work vocally, makes this a much more powerful way of interacting with a coding agent.

    ↗A new feature for my blog, built using my voicesimonwillison.net

    9 Oct 2026

Incentives

Look at what people are rewarded for; it explains more behaviour than what they say, your own included.

Used by 84 others

The frontier labs optimise their models for code above everything else because coding is where the money is: developers will pay $200 a month once a model is good enough.

  1. Simon Willison Co-creator of Django and creator of Datasette OpenAI and Anthropic have both realized that code is the most important thing to optimize the models for, cuz that's where the money is. Like coders will spend $200 a month on a plan if it's good enough, it turns out. Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com · 19 Mar 2026 · 20:24 into the videoAll korrents from this video
    Their wordsOpenAI and Anthropic have both realized that code is the most important thing to optimize the models for, cuz that's where the money is. Like coders will spend $200 a month on a plan if it's good enough, it turns out.

    Where this was said

    Watch from 20:24 plays here

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com

    19 Mar 2026 · video · 28m · spoken · machine transcript

Margin of safety

Leave room for being wrong, because sometimes you will be.

Used by 25 others

Running 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.

  1. Simon Willison Co-creator of Django and creator of Datasette I 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 · 31 Dec 2025
    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

    31 Dec 2025

The map is not the territory

Every model, word or plan is a simplified map of reality; useful when its structure matches, misleading when mistaken for the thing itself.

Used by 55 others

A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would.

  1. Simon Willison Co-creator of Django and creator of Datasette 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 · 19 Mar 2026 · 7:16 into the videoAll korrents from this video
    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.

    Where this was said

    Watch from 7:16 plays here

    ↗Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summityoutube.com

    19 Mar 2026 · video · 28m · spoken · machine transcript