Flux
Toutes les catégories

Programmation

2113 articles

Quoting Georgi Gerganov

Quoting Georgi Gerganov

Note that the main issues that people currently unknowingly face with local models mostly revolve around the harness and some intricacies around model chat templates and prompt construction. Sometimes there are even pure inference bugs. From typing the task in the client to the actual result, there is a long chain of components that atm are not only fragile - are also developed by different parties. So it's difficult to consolidate the entire stack and you have to keep in mind that what you are…

Simon Willison's Weblog
Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer

Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer

Trip Venturella released Mr. Chatterbox, a language model trained entirely on out-of-copyright text from the British Library. Here's how he describes it in the model card: Mr. Chatterbox is a language model trained entirely from scratch on a corpus of over 28,000 Victorian-era British texts published between 1837 and 1899, drawn from a dataset made available by the British Library. The model has absolutely no training inputs from after 1899 — the vocabulary and ideas are formed exclusively from…

Simon Willison's Weblog
★ Scotty: a beautiful SSH task runner

★ Scotty: a beautiful SSH task runner

We just released Scotty, a beautiful SSH task runner. It lets you define deploy scripts and other remote tasks, run them from your terminal, and watch every step as it happens. It supports both Laravel Envoy's Blade format and a new plain bash format. Why we built Scotty Even though services like Laravel Cloud make it possible to never think about servers again, I still prefer deploying to my own servers for some projects. I know my way around them, I can pick whichever server provider I want,…

Freek Van der Herten
Pretext

Pretext

Pretext Exciting new browser library from Cheng Lou, previously a React core developer and the original creator of the react-motion animation library. Pretext solves the problem of calculating the height of a paragraph of line-wrapped text without touching the DOM. The usual way of doing this is to render the text and measure its dimensions, but this is extremely expensive. Pretext uses an array of clever tricks to make this much, much faster, which enables all sorts of new text rendering…

Simon Willison's Weblog
Python Vulnerability Lookup

Python Vulnerability Lookup

Tool: Python Vulnerability Lookup I learned that the OSV.dev open source vulnerability database has an open CORS JSON API, so I had Claude Code build this HTML tool for pasting in a pyproject.toml or requirements.txt file (or name of a GitHub repo containing those) and seeing a list of all reported vulnerabilities from that API. Tags: tools, python, supply-chain, vibe-coding, security

Simon Willison's Weblog
Quoting Matt Webb

Quoting Matt Webb

The thing about agentic coding is that agents grind problems into dust. Give an agent a problem and a while loop and - long term - it’ll solve that problem even if it means burning a trillion tokens and re-writing down to the silicon. [...] But we want AI agents to solve coding problems quickly and in a way that is maintainable and adaptive and composable (benefiting from improvements elsewhere), and where every addition makes the whole stack better. So at the bottom is really great libraries…

Simon Willison's Weblog
Quoting Richard Fontana

Quoting Richard Fontana

FWIW, IANDBL, TINLA, etc., I don’t currently see any basis for concluding that chardet 7.0.0 is required to be released under the LGPL. AFAIK no one including Mark Pilgrim has identified persistence of copyrightable expressive material from earlier versions in 7.0.0 nor has anyone articulated some viable alternate theory of license violation. [...] — Richard Fontana, LGPLv3 co-author, weighing in on the chardet relicensing situation Tags: open-source, ai-ethics, llms, ai, generative-ai,…

Simon Willison's Weblog
Vibe coding SwiftUI apps is a lot of fun

Vibe coding SwiftUI apps is a lot of fun

I have a new laptop - a 128GB M5 MacBook Pro, which early impressions show to be very capable for running good local LLMs. I got frustrated with Activity Monitor and decided to vibe code up some alternative tools for monitoring performance and I'm very happy with the results. This is my second experiment with vibe coding macOS apps - the first was this presentation app a few weeks ago. It turns out Claude Opus 4.6 and GPT-5.4 are both very competent at SwiftUI - and a full SwiftUI app can fit…

Simon Willison's Weblog