Flux
Couleur d'accent
Toutes les catégories

Programmation

3647 articles

llm-coding-agent 0.1a0

llm-coding-agent 0.1a0

Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new Python library using my python-lib-template-repository GitHub template repository, then ran these two prompts (here's the Claude Code for web transcript): Write a spec.md for this project - it will depend on the latest “llm” alpha from PyPI and implement a Claude code style coding…

Simon Willison's Weblog
Using DSPy to evaluate and improve Datasette Agent's SQL system prompts

Using DSPy to evaluate and improve Datasette Agent's SQL system prompts

Research: Using DSPy to evaluate and improve Datasette Agent's SQL system prompts One of this morning's AIE keynotes covered dspy, which reminded me I've been meaning to see if it could help me improve the system prompt used by Datasette Agent - so I fired off an asynchronous research task in Claude Code for web using Claude Fable 5: Pip install the latest Datasette alpha and datasette-agent and dspy - then figure out how to use dspy to evaluate and improve the main system prompts used by…

Simon Willison's Weblog
Understand to participate

Understand to participate

I saw Geoffrey Litt speak at AIE yesterday, and one framing he used particularly resonated with me: Understand to participate Geoffrey was talking about the challenge of collaborating with coding agents as they construct increasingly large and sophisticated changes, and the need to avoid taking on cognitive debt as your understanding drifts from how the code actually works. His argument is that you need to understand the code to a depth that enables you to participate further with the model:…

Simon Willison's Weblog
How to run multiple AI agents in parallel with git worktrees

How to run multiple AI agents in parallel with git worktrees

Video version: https://youtu.be/uVKXmqYVjpQ One of the more powerful features of AI-assisted development is that you can put multiple AI coding agents to work simultaneously with little effort. For example, you might have one building a new feature, one cleaning up an old API endpoint, and a third drafting a blog post. If the agents share […] The post How to run multiple AI agents in parallel with git worktrees appeared first on PHP Architect.

PHP Architect
Case Study: Driving Green Innovation: How Symfony Empowered Veolia’s Digital Shift in Industrial Waste Management

Case Study: Driving Green Innovation: How Symfony Empowered Veolia’s Digital Shift in Industrial Waste Management

When dealing with over 10 million tons of hazardous waste every year, IT operational efficiency is a prerquisite and a critical environmental and public health responsibility As the European leader in treating hazardous industrial waste and restoring…

Symfony Blog
PolinRider: North Korea-Linked Supply Chain Campaign Expands Across Open Source Ecosystems

PolinRider: North Korea-Linked Supply Chain Campaign Expands Across Open Source Ecosystems

Socket Threat Research Team identified 162 malicious release artifacts across 108 packages and extensions in npm, Packagist, Go modules, and Chrome extensions, linking the activity to the broader North Korean Contagious Interview / Famous Chollima developer-targeting campaign. PolinRider is a supply chain campaign linked to North Korean threat actors associated with the broader Contagious Interview / Famous Chollima activity cluster. Our latest findings show that the campaign has expanded…

Socket
MySQL Recursive CTEs for PHP Developers: Querying Hierarchical Data Without the Pain

MySQL Recursive CTEs for PHP Developers: Querying Hierarchical Data Without the Pain

Recursive CTEs in MySQL let you query trees, org charts, and nested categories in a single query. Here’s how to use them effectively with PHP. Every PHP developer eventually hits the “tree problem.” You have categories with subcategories, employees with managers, comments with replies, or menu items with children — and you need to query […] The post MySQL Recursive CTEs for PHP Developers: Querying Hierarchical Data Without the Pain appeared first on PHP Architect.

PHP Architect
Meet TYPO3: Supporting the Open-Source Foundation of Its Ecosystem

Meet TYPO3: Supporting the Open-Source Foundation of Its Ecosystem

TYPO3 has joined the PHP Foundation as a Silver Sponsor, extending its commitment to the open-source technologies and communities on which its own ecosystem is built. TYPO3 is an open-source enterprise content management system built with open web standards. It provides a robust feature set for scalable, multisite, multilingual, and highly connected digital platforms. TYPO3 is also a verified Digital Public Good and part of the Open Website Alliance through the TYPO3 Association. PHP: the…

The PHP Foundation
Nano Banana 2 Lite

Nano Banana 2 Lite

Nano Banana 2 Lite Also known as Gemini 3.1 Flash Lite Image (gemini-3.1-flash-lite-image in their API), this is the "fastest and cheapest Gemini image model, engineered for velocity and scale". I used AI studio to run this prompt: Do a where's Waldo style image but it's where is the raccoon holding a ham radio I like that one better than the results I got from the other Nano Banana models when I tried this back in April. It spelled Forest Festival wrong in two different ways though. Via Hacker…

Simon Willison's Weblog
Risky Biz Podcast: AI Agents Are Raising the Stakes for Software Supply Chain Security

Risky Biz Podcast: AI Agents Are Raising the Stakes for Software Supply Chain Security

The last six months have been one of the most intense stretches of software supply chain attacks the open source ecosystem has seen. Attackers are compromising widely used packages, abusing trusted developer workflows, stealing credentials, and using package registries, IDE extensions, and source repositories to distribute malicious code. At the same time, AI coding agents are changing how software gets built, pulling in dependencies at machine speed and making unreviewed trust decisions…

Socket
What's new in Claude Sonnet 5

What's new in Claude Sonnet 5

What's new in Claude Sonnet 5 Claude Sonnet 5 came out this morning. I always head straight for the "what's new" developer docs because they tend to have more actionable information than the official announcement post. Anthropic say of Sonnet 5 that "its performance is close to that of Opus 4.8, but at lower prices". The system card helps explain how they were able to release the model without being blocked by the US government: Sonnet 5 is significantly less capable at cyber tasks than…

Simon Willison's Weblog
The AI Compass

The AI Compass

The AI Compass This political compass style quiz by bambamramfan is pretty neat - answer 29 questions about AI and AI ethics to see which of the 30 archetypes you best fit. I'm impressed that my answers on my first time through the quiz categorized me as "The Garage Tinkerer", patron saint myself! It's implemented as a single page React app using the <script type="text/babel"> trick to avoid the necessary build step. Here's the code. Via @erisianrite.com Tags: ai, generative-ai, llms,…

Simon Willison's Weblog
Have your agent record video demos of its work with shot-scraper video

Have your agent record video demos of its work with shot-scraper video

shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to record a video of that routine. I've written before about the importance of having coding agents produce demos of their work; this is my latest attempt at enabling them to do that. Here's an example video created using shot-scraper video, exercising a still in development feature adding the ability to…

Simon Willison's Weblog
Esc