Flux
llm 0.32a2
IA Programmation

llm 0.32a2

Release: llm 0.32a2 A bunch of useful stuff in this LLM alpha, but the most important detail is this one: Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables interleaved reasoning across tool calls for GPT-5 class models. #1435 This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if you don't…

Simon Willison's Weblog
Burnout and Cognitive Debt
IA

Burnout and Cognitive Debt

Steve Yegge’s article about programmer burnout (“The AI Vampire”) along with Margaret Storey’s article about Cognitive Debt started an ongoing conversation about programmer fatigue and software quality—two topics that should be linked, but often aren’t. Steve argues that programming constantly with the help of agentic AI leds to burnout; it’s fast, it’s fun, but keeping […]

O'Reilly Radar — AI/ML
Socket Named to Rising in Cyber 2026 List of Top Cybersecurity Startups
Cybersécurité Programmation

Socket Named to Rising in Cyber 2026 List of Top Cybersecurity Startups

Socket has been named to the Rising in Cyber 2026 list, an annual recognition of the most promising private cybersecurity companies, as selected by nearly 150 practicing CISOs and cybersecurity executives. Launched by Notable Capital, Rising in Cyber recognizes 30 private cybersecurity startups shaping the future of enterprise security. This year’s honorees were selected by security leaders from organizations including Booking.com, Albertsons, Atlassian, and TIAA. The list was announced…

Socket
Thoughts on GitLab's workforce reduction" and "structural and strategic decisions"
IA Programmation

Thoughts on GitLab's workforce reduction" and "structural and strategic decisions"

GitLab Act 2 There's a lot going on in this announcement from GitLab about the "workforce reduction" and "structural and strategic decisions" they are making with respect to the agentic era. They're "planning to reduce the number of countries by up to 30% where we have small teams". One of the most interesting things about GitLab is that they have employees spread across a large number of countries - 18 are listed in their public employee handbook but this post says they are "operating in…

Simon Willison's Weblog
TanStack npm Packages Compromised in Ongoing Mini Shai-Hulud Supply-Chain Attack
Cybersécurité Programmation

TanStack npm Packages Compromised in Ongoing Mini Shai-Hulud Supply-Chain Attack

The Socket Threat Research team detected a compromise across 84 npm package artifacts in the tanstack namespace. Affected packages were modified to add a suspected credential stealer targeting various CI systems, including Github Actions. All packages were flagged by Socket AI Scanner in six minutes or less after publication. Several of the newly turned malicious packages, like pkg:npm/@tanstack/react-router have over 12 million weekly downloads, and are widely consumed both directly and…

Socket
Quoting James Shore
IA Programmation

Quoting James Shore

Your AI coding agent, the one you use to write code, needs to reduce your maintenance costs. Not by a little bit, either. You write code twice as quick now? Better hope you’ve halved your maintenance costs. Three times as productive? One third the maintenance costs. Otherwise, you’re screwed. You’re trading a temporary speed boost for permanent indenture. [...] The math only works if the LLM decreases your maintenance costs, and by exactly the inverse of the rate it adds code. If you double…

Simon Willison's Weblog
Your AI Use Is Breaking My Brain
IA Programmation

Your AI Use Is Breaking My Brain

Your AI Use Is Breaking My Brain Excellent, angry piece by Jason Koebler on how AI writing online is becoming impossible to avoid, filtering it is mentally exhausting and it's even starting to distort regular human writing styles. I particularly liked his use of the term "Zombie Internet" to define a different, more insidious alternative to the "Dead Internet" (which is just bots talking to each other): I called it the Zombie Internet because the truth is that large parts of the internet are…

Simon Willison's Weblog
Using LLM in the shebang line of a script
IA Programmation

Using LLM in the shebang line of a script

TIL: Using LLM in the shebang line of a script Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) [...] This inspired me to look at patterns for doing exactly that with LLM. Here's the simplest, which takes advantage of LLM fragments: #!/usr/bin/env -S llm -f Generate an SVG of a pelican riding a bicycle But you can also incorporate tool calls using the -T name_of_tool option: #!/usr/bin/env -S llm -T llm_time -f Write a…

Simon Willison's Weblog
Learning on the Shop floor
IA Programmation

Learning on the Shop floor

Learning on the Shop floor Tobias Lütke describes Shopify's internal coding agent tool, River, which operates entirely in public on their Slack: River does not respond to direct messages. She politely declines and suggests to create a public channel for you and her to start working in. I myself work with river in #tobi_river channel and many followed this pattern. Every conversation is therefore searchable. Anyone at Shopify can jump in. In my own channel, there are over 100 people who, react…

Simon Willison's Weblog