Flux
Couleur d'accent
GPT-5.5 prompting guide
IA Programmation

GPT-5.5 prompting guide

GPT-5.5 prompting guide Now that GPT-5.5 is available in the API, OpenAI have released a wealth of useful tips on how best to prompt the new model. Here's a neat trick they recommend for applications that might spend considerable time thinking before returning a user-visible response: Before any tool calls for a multi-step task, send a short user-visible update that acknowledges the request and states the first step. Keep it to one or two sentences. I've already noticed their Codex app doing…

Simon Willison's Weblog
73 Open VSX Sleeper Extensions Linked to GlassWorm Show New Malware Activations
Cybersécurité Programmation

73 Open VSX Sleeper Extensions Linked to GlassWorm Show New Malware Activations

The GlassWorm campaign targeting Open VSX continues to escalate. Socket is now tracking a new cluster of 73 impersonation extensions connected to the same sleeper-extension activity reported in March 2026. Beginning in April 2026, and continuing as of this writing, additional cloned versions of popular code extensions have appeared on the Open VSX marketplace. These extensions did not initially contain malware, but they were published by newly created GitHub accounts with only one or two public…

Socket
llm 0.31
IA Programmation

llm 0.31

Release: llm 0.31 New GPT-5.5 OpenAI model: llm -m gpt-5.5. #1418 New option to set the text verbosity level for GPT-5+ OpenAI models: -o verbosity low. Values are low, medium, high. New option for setting the image detail level used for image attachments to OpenAI models: -o image_detail low - values are low, high and auto, and GPT-5.4 and 5.5 also accept original. Models listed in extra-openai-models.yaml are now also registered as asynchronous. #1395 Tags: gpt, openai, llm

Simon Willison's Weblog
The people do not yearn for automation
IA Programmation

The people do not yearn for automation

The people do not yearn for automation This written and video essay by Nilay Patel explores why AI is unpopular with the general public even as usage numbers for ChatGPT continue to skyrocket. It’s a superb piece of commentary, and something I expect I’ll be thinking about for a long time to come. Nilay’s core idea is that people afflicted with “software brain” - who see the world as something to be automated as much as possible, and attempt to model everything in terms of information flows and…

Simon Willison's Weblog
Introducing Reachability for PHP
Cybersécurité Programmation

Introducing Reachability for PHP

Security teams are already struggling to keep pace with the volume of vulnerability disclosures. Every week brings more CVEs, and the arrival of AI-assisted vulnerability research is only going to push that number higher. Teams that can't tell which disclosures actually matter for their application will fall behind quickly. PHP carries more of this weight than most ecosystems. Composer ranks third for CVE volume among package ecosystems, behind only Maven and npm, and PHP still runs a…

Socket
Emergency Pedagogical Design: How Programming Instructors Are Scrambling to Adapt to GenAI
IA

Emergency Pedagogical Design: How Programming Instructors Are Scrambling to Adapt to GenAI

ChatGPT has been publicly available for over three years now, and generative AI is woven into the tools students use every day: web search, word processors, code editors. You might assume that by now, most programming instructors have figured out how to handle it. But when my collaborators and I went looking for computing instructors […]

O'Reilly Radar — AI/ML
DeepSeek V4 - almost on the frontier, a fraction of the price
IA Programmation

DeepSeek V4 - almost on the frontier, a fraction of the price

Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V4-Pro and DeepSeek-V4-Flash. Both models are 1 million token context Mixture of Experts. Pro is 1.6T total parameters, 49B active. Flash is 284B total, 13B active. They're using the standard MIT license. I think this makes DeepSeek-V4-Pro the new largest open weights model. It's larger than Kimi…

Simon Willison's Weblog
It's a big one
IA Programmation

It's a big one

This week's edition of my email newsletter (aka content from this blog delivered to your inbox) features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide. Tags: newsletter

Simon Willison's Weblog
Esc