Flux
Couleur d'accent
Toutes les catégories

IA

2448 articles

A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView
IA Programmation

A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView

Research: A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView Today saw the long awaited release of Bun 1.4, the first stable version since the infamous Rust rewrite a few months ago. Interestingly, the Rust rewrite was downplayed in the release notes, which introduced a bewildering array of new features and claimed 2,900 additional bug fixes: Bun 1.4 adds +1,517 tests from the Node.js test suite - our biggest jump in Node.js compatibility since Bun 1.0. Bun v1.4 also fixes over…

Simon Willison's Weblog
smolmachines / smolvm as a sandbox for untrusted Python & JavaScript
IA Programmation

smolmachines / smolvm as a sandbox for untrusted Python & JavaScript

Research: smolmachines / smolvm as a sandbox for untrusted Python & JavaScript I tasked Claude Fable 5 running in Claude Code for web with the following research task: Put https://smolmachines.com through its paces as a fast secure sandbox. Explore what it would take to use this to run untrusted Python and JavaScript code in a way that is limited in what RAM and CPU time it can take up (protection against "while true") with no network access and filesystem access only to designated files…

Simon Willison's Weblog
Quoting Jeremy Morrell
IA Programmation

Quoting Jeremy Morrell

My hypothesis is that there is a new opportunity for Extensible Software on the web. LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and provide good security boundaries. We can build our app as a solid, accountable core, and allow users to safely extend it in many directions by having LLMs fill in the missing pieces. We can give our users super powers. — Jeremy Morrell, Extensible Software in the age of LLMs Tags: sandboxing,…

Simon Willison's Weblog
Conceptual integrity and counting lines of code
IA Programmation

Conceptual integrity and counting lines of code

Last week I recorded an episode of the Talking Postgres podcast with Claire Giordano on the subject of "How AI is changing software development". We had a really great conversation. Here are a couple of my highlights from a lightly edited transcript (prompt to Claude: "very minor edits to remove disfluencies"). This is the latest version of an argument I've been trying to build about why sometimes it does make sense to talk about lines of code as an indicator of productivity with coding agents,…

Simon Willison's Weblog
When Your Buyer Is an AI Agent
IA

When Your Buyer Is an AI Agent

In 2021, Maersk, the world’s largest container shipping company, deployed AI agents from a startup called Pactum to negotiate freight lane contracts with its carrier suppliers. The objective was for AI agents to handle negotiations autonomously rather than merely support human procurement staff. Operating entirely autonomously, the system manages the end-to-end agreement process, from reaching […]

O'Reilly Radar — AI/ML
When Guardrails Go Wrong
IA

When Guardrails Go Wrong

The latest round of restrictions and safeguards for frontier models are overly fussy and limiting. A Claude skill that I created demonstrates what happens when guardrails go astray. My skill helps me to find articles and blog posts that go into O’Reilly Radar’s monthly Trends to Watch. It reads roughly a dozen well-known sites like […]

O'Reilly Radar — AI/ML
Mojo🔥 is now open source
IA Programmation

Mojo🔥 is now open source

Mojo🔥 is now open source Mojo🔥 is now open source The Mojo programming language has been promising an open source release since May 2023. Last week they shipped their 1.0 and today they have followed through on that original promise, releasing the compiler and toolchain under an Apache 2 license. When Mojo first launched the stated goal was to produce a superset of Python, so existing Python code could be used to bootstrap their own ecosystem. That plan changed around August 2025: Mojo may or…

Simon Willison's Weblog
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index
IA Programmation

Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index

Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.6 Luna (max), and just one point behind GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max) - that GLM is 753B and that DeepSeek is 1.6B parameters, and Luna is size unknown but presumably a whole lot bigger than 27B. Qwen 3.8 27B is a truly astonishing model. Via Hacker News Tags: ai, generative-ai, llms, qwen, ai-in-china, artificial-analysis

Simon Willison's Weblog
What’s an Orchestrator—and Why Does Software Need One?
IA

What’s an Orchestrator—and Why Does Software Need One?

The following article originally appeared on Medium and is being republished here with the author’s permission. Everybody’s talking about the death of developers. I get it. The developer whose job was to write boilerplate or scaffold CRUD apps is done—a model can do that in seconds, and that developer is not coming back. But the […]

O'Reilly Radar — AI/ML
Esc