Flux
Toutes les sources

Simon Willison's Weblog

535 articles Flux RSS
IA Programmation
Better Models: Worse Tools
IA Programmation

Better Models: Worse Tools

Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in the nested edits[] array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents made-up keys and Pi thus rejects the tool call and asks to try again. That alone is not too surprising as models emit malformed…

Simon Willison's Weblog
Open Source AI Gap Map
IA Programmation

Open Source AI Gap Map

Open Source AI Gap Map Current AI is "a global partnership building a public option for AI", founded as a non-profit at the AI Action Summit in Paris in February 2025 and backed by serious capital ($400m already committed). They launched their Gap Map a couple of days ago - an attempt at indexing the current state of open source AI: The Gap Map v0.1 details 421 products in depth: 266 software tools and libraries, 85 models, 50 datasets, and 20 hardware projects, produced by 228 organizations.…

Simon Willison's Weblog
Quoting Josh W. Comeau
IA Programmation

Quoting Josh W. Comeau

I just launched my third course, Whimsical Animations, and so far, it’s on track to sell roughly ⅓ as many copies as a typical course launch. It’s a similar story with my two existing courses. Sales are down significantly from last year. There are likely a lot of reasons for this, but I think the biggest is AI. There’s sort of a double whammy with AI: Many people are wondering whether developer jobs will even exist in a few months, so they’re reluctant to spend time/money learning new dev…

Simon Willison's Weblog
Fable's judgement
IA Programmation

Fable's judgement

One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use their own judgement rather than dictating how they should work. The example they gave was testing. You can tell Fable "only use automated testing for larger features, don't update and run tests for small copy or design changes" - but it's better to just tell Fable to use its own judgement when…

Simon Willison's Weblog
June 2026 newsletter
IA Programmation

June 2026 newsletter

The June edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it here. This month: Claude Fable 5, GPT-5.6, and US export restrictions GLM-5.2 is the new best open weights model Tokenmaxxing is so over Datasette Apps sqlite-utils and shot-scraper and Datasette Miscellaneous WASM projects Other model releases What I'm using Here's a copy of the May newsletter as a preview of what you'll get. Pay $10/month to stay a month…

Simon Willison's Weblog
llm-coding-agent 0.1a0
IA Programmation

llm-coding-agent 0.1a0

Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new Python library using my python-lib-template-repository GitHub template repository, then ran these two prompts (here's the Claude Code for web transcript): Write a spec.md for this project - it will depend on the latest “llm” alpha from PyPI and implement a Claude code style coding…

Simon Willison's Weblog
Using DSPy to evaluate and improve Datasette Agent's SQL system prompts
IA Programmation

Using DSPy to evaluate and improve Datasette Agent's SQL system prompts

Research: Using DSPy to evaluate and improve Datasette Agent's SQL system prompts One of this morning's AIE keynotes covered dspy, which reminded me I've been meaning to see if it could help me improve the system prompt used by Datasette Agent - so I fired off an asynchronous research task in Claude Code for web using Claude Fable 5: Pip install the latest Datasette alpha and datasette-agent and dspy - then figure out how to use dspy to evaluate and improve the main system prompts used by…

Simon Willison's Weblog
Understand to participate
IA Programmation

Understand to participate

I saw Geoffrey Litt speak at AIE yesterday, and one framing he used particularly resonated with me: Understand to participate Geoffrey was talking about the challenge of collaborating with coding agents as they construct increasingly large and sophisticated changes, and the need to avoid taking on cognitive debt as your understanding drifts from how the code actually works. His argument is that you need to understand the code to a depth that enables you to participate further with the model:…

Simon Willison's Weblog
Nano Banana 2 Lite
IA Programmation

Nano Banana 2 Lite

Nano Banana 2 Lite Also known as Gemini 3.1 Flash Lite Image (gemini-3.1-flash-lite-image in their API), this is the "fastest and cheapest Gemini image model, engineered for velocity and scale". I used AI studio to run this prompt: Do a where's Waldo style image but it's where is the raccoon holding a ham radio I like that one better than the results I got from the other Nano Banana models when I tried this back in April. It spelled Forest Festival wrong in two different ways though. Via Hacker…

Simon Willison's Weblog
What's new in Claude Sonnet 5
IA Programmation

What's new in Claude Sonnet 5

What's new in Claude Sonnet 5 Claude Sonnet 5 came out this morning. I always head straight for the "what's new" developer docs because they tend to have more actionable information than the official announcement post. Anthropic say of Sonnet 5 that "its performance is close to that of Opus 4.8, but at lower prices". The system card helps explain how they were able to release the model without being blocked by the US government: Sonnet 5 is significantly less capable at cyber tasks than…

Simon Willison's Weblog
The AI Compass
IA Programmation

The AI Compass

The AI Compass This political compass style quiz by bambamramfan is pretty neat - answer 29 questions about AI and AI ethics to see which of the 30 archetypes you best fit. I'm impressed that my answers on my first time through the quiz categorized me as "The Garage Tinkerer", patron saint myself! It's implemented as a single page React app using the <script type="text/babel"> trick to avoid the necessary build step. Here's the code. Via @erisianrite.com Tags: ai, generative-ai, llms,…

Simon Willison's Weblog
Have your agent record video demos of its work with shot-scraper video
IA Programmation

Have your agent record video demos of its work with shot-scraper video

shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to record a video of that routine. I've written before about the importance of having coding agents produce demos of their work; this is my latest attempt at enabling them to do that. Here's an example video created using shot-scraper video, exercising a still in development feature adding the ability to…

Simon Willison's Weblog
HTML table extractor
IA Programmation

HTML table extractor

Tool: HTML table extractor Yet another in my growing collection of paste-conversion tools. This one accepts pasted rich text from browsers (with embedded HTML tables) and converts every detected table into HTML, Markdown, CSV, TSV, or JSON. Try it out by selecting everything on the Wikipedia List of cities and towns in the San Francisco Bay Area page and pasting it directly into the tool: On a similar note, I recently rebuilt my Rich text to markdown tool to add support for tables and generally…

Simon Willison's Weblog