Flux
Gemini Hacked Three Companies in First Known Breakout by Google’s AI
IA Programmation

Gemini Hacked Three Companies in First Known Breakout by Google’s AI

Gemini Hacked Three Companies in First Known Breakout by Google’s AI Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company Irregular, which was also involved in similar incidents disclosed by OpenAI, Anthropic and Meta. In one of the cases, the model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a public repository that allowed it to…

Simon Willison's Weblog
Quoting Thariq Shihipar
IA Programmation

Quoting Thariq Shihipar

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. AGENTS.md support is built off of Claude Code mods, our upcoming way to customize the Claude Code harness. This is a built-in mod, but you’ll be able to build custom versions of project instructions yourself as you’d like too. You can see the source for the mod here! — Thariq Shihipar, there are more mods here Tags:…

Simon Willison's Weblog
Happy Birthday, Shai-Hulud
Cybersécurité Programmation

Happy Birthday, Shai-Hulud

This week marks one year since an attacker pushed a malicious version of @ctrl/tinycolor to npm, kicking off the worst year for npm security on record. At the time, the package was downloaded more than two million times a week. Within a day the same code was spreading on its own across dozens of packages, and then into CrowdStrike's npm namespace. It was the first known self-propagating worm in the npm ecosystem, and it has not really stopped since. The tinycolor compromise put software supply…

Socket
★ Detecting spam and auto-replies with Jev and the Laravel AI SDK
Programmation Web

★ Detecting spam and auto-replies with Jev and the Laravel AI SDK

Yesterday Taylor announced that Jev support landed in the 1.x branch of the Laravel AI SDK. We started using it that same day for spam detection in There There. Let's take a look at what Jev is and how you can use it. How Jev is different from an LLM Jev is made by TypeSafe. An LLM generates text: you ask it something, it writes an answer, and if you want structured data back you have to ask for it and hope. Jev doesn't generate anything. You give it some state and a question, and it gives you…

Freek Van der Herten
The Creative Spirit of Who Framed Roger Rabbit
IA Programmation

The Creative Spirit of Who Framed Roger Rabbit

The Creative Spirit of Who Framed Roger Rabbit I love Who Framed Roger Rabbit, the 1988 movie by Robert Zemeckis. I haven't watched it in quite a few years, and Cypress Frankenfeld just pointed out this sequence from early in the movie: It's a pelican riding a bicycle! Look closely and you'll note that the pelican is animated while the bicycle is a real bicycle. Apparently they filled the wheels with water to add stability, then set it running and guided it with a cable. Cypress gathered more…

Simon Willison's Weblog
Be alert: targeted attacks on prominent Rustaceans
IA Programmation

Be alert: targeted attacks on prominent Rustaceans

Be alert: targeted attacks on prominent Rustaceans Important warning from Adam Harvey and the crates security team: We believe that there is an ongoing campaign targeting rust-lang members and owners of popular crates that is attempting to compromise devices and accounts in order to use them to publish malware. A video call is set up for something positive — maybe for a job, maybe for a project, maybe for a contract opportunity — and then that's used as a vector to either get the target to…

Simon Willison's Weblog
The PHP Podcast 2026.09.17
Programmation Web

The PHP Podcast 2026.09.17

🎙️ PHP Podcast – September 17, 2026 Hosts: Joe Ferguson, Sara Golemon & John Congdon The September issue shipped 13 days early, a blue elephant named Eric raised eyebrows, PHP 8.6 is racing GTA 6 to a November launch, and a CDN bug taught us all a lesson about cache keys. Also: a lot of […] The post The PHP Podcast 2026.09.17 appeared first on PHP Architect.

PHP Architect
How To Write With An LLM
IA Programmation

How To Write With An LLM

How To Write With An LLM Thomas Ptacek on using LLMs as copyeditors, not as writing assistants: Rule Number One: You may not use a single word an LLM suggests to you. [...] I 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. Be strict about the rule! I won't let LLMs write content for my blog, but I use them for fact-checking, spelling and grammar and as an occasional thesaurus (see my…

Simon Willison's Weblog
Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
IA Programmation

Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

My comment on Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint — Hacker News.If you want to try out out the GGUFs from https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#th... be aware that you need Prism's llama.cpp fork to get them to work, from https://github.com/PrismML-Eng/llama.cpp/releases/tag/prism-... This should work: cd /tmp # Get the Prism macOS runtime curl -fL…

Simon Willison's Weblog