Flux
Toutes les catégories

Programmation

1004 articles

Quoting Andreas Påhlsson-Notini
IA Programmation

Quoting Andreas Påhlsson-Notini

AI agents are already too human. Not in the romantic sense, not because they love or fear or dream, but in the more banal and frustrating one. The current implementations keep showing their human origin again and again: lack of stringency, lack of patience, lack of focus. Faced with an awkward task, they drift towards the familiar. Faced with hard constraints, they start negotiating with reality. — Andreas Påhlsson-Notini, Less human AI agents, please. Tags: ai-agents, coding-agents, ai

Simon Willison's Weblog
Introducing Reports: An Extensible Reporting Framework for Socket Data
Cybersécurité Programmation

Introducing Reports: An Extensible Reporting Framework for Socket Data

Today, we’re introducing Reports, a new page in the Socket dashboard for chart-based views of vulnerabilities, dependencies, and usage. At launch, Reports includes five built-in charts across three categories, with support for organization-wide and repository-level views. It replaces the previous Analytics page with a more structured reporting experience in the dashboard. Built as an extensible reporting framework, the new page gives teams a more consistent way to work with and share Socket…

Socket
Ubuntu Firewall Setup in Less Than 5 Minutes (Plus One Step That Will Lock You Out)
Programmation Web

Ubuntu Firewall Setup in Less Than 5 Minutes (Plus One Step That Will Lock You Out)

Setting up a Virtual Private Server (VPS) without a firewall is asking for trouble. Ideally, you’d have a dedicated security person to handle all of this, but that’s rarely the case. One thing I always do on a fresh Linux server is configure a firewall. It used to be a real headache, but […] The post Ubuntu Firewall Setup in Less Than 5 Minutes (Plus One Step That Will Lock You Out) appeared first on PHP Architect.

PHP Architect
Socket for Jira Is Now Available
Cybersécurité Programmation

Socket for Jira Is Now Available

Security findings only matter if organizations can act on them. That usually means getting the right issues into the systems where engineering and security teams already work. Socket for Jira is now available, making it easy to turn Socket alerts into Jira issues and keep remediation work moving as alerts change over time. Teams can create tickets manually from individual alerts or set up automated ticketing rules to create, update, and resolve issues based on activity in Socket. The…

Socket
llm-openrouter 0.6
IA Programmation

llm-openrouter 0.6

Release: llm-openrouter 0.6 llm openrouter refresh command for refreshing the list of available models without waiting for the cache to expire. I added this feature so I could try Kimi 2.6 on OpenRouter as soon as it became available there. Here's its pelican - this time as an HTML page because Kimi chose to include an HTML and JavaScript UI to control the animation. Transcript here. Tags: openrouter, llm, llm-release, pelican-riding-a-bicycle, kimi, ai-in-china, llms, ai, generative-ai

Simon Willison's Weblog
SQL functions in Google Sheets to fetch data from Datasette
IA Programmation

SQL functions in Google Sheets to fetch data from Datasette

TIL: SQL functions in Google Sheets to fetch data from Datasette I put together some notes on patterns for fetching data from a Datasette instance directly into Google Sheets - using the importdata() function, a "named function" that wraps it or a Google Apps Script if you need to send an API token in an HTTP header (not supported by importdata().) Here's an example sheet demonstrating all three methods. Tags: spreadsheets, datasette, google

Simon Willison's Weblog
Claude Token Counter, now with model comparisons
IA Programmation

Claude Token Counter, now with model comparisons

Claude Token Counter, now with model comparisons I upgraded my Claude Token Counter tool to add the ability to run the same count against different models in order to compare them. As far as I can tell Claude Opus 4.7 is the first model to change the tokenizer, so it's only worth running comparisons between 4.7 and 4.6. The Claude token counting API accepts any Claude model ID though so I've included options for all four of the notable current models (Opus 4.7 and 4.6, Sonnet 4.6, and Haiku…

Simon Willison's Weblog
Headless everything for personal AI
IA Programmation

Headless everything for personal AI

Headless everything for personal AI Matt Webb thinks headless services are about to become much more common: Why? Because using personal AIs is a better experience for users than using services directly (honestly); and headless services are quicker and more dependable for the personal AIs than having them click round a GUI with a bot-controlled mouse. Evidently Marc Benioff thinks so too: Welcome Salesforce Headless 360: No Browser Required! Our API is the UI. Entire Salesforce & Agentforce…

Simon Willison's Weblog
Changes in the system prompt between Claude Opus 4.6 and 4.7
IA Programmation

Changes in the system prompt between Claude Opus 4.6 and 4.7

Anthropic are the only major AI lab to publish the system prompts for their user-facing chat systems. Their system prompt archive now dates all the way back to Claude 3 in July 2024 and it's always interesting to see how the system prompt evolves as they publish new models. Opus 4.7 shipped the other day (April 16, 2026) with a Claude.ai system prompt update since Opus 4.6 (February 5, 2026). I had Claude Code take the Markdown version of their system prompts, break that up into separate…

Simon Willison's Weblog
Esc