Training a 4B model to produce 81% faster query plans than Postgres
...or how to make Qwen learn query optimisation via agentic reinforcement learning
Topic
Agent engineering
Pion, an agent designed to run any company autonomously
Pion is the platform Andonlabs built to run Andonlabs’ autonomous businesses. Today Andonlabs is opening it up so many more people can experiment…
Why are AI agents lying, cheating and coordinating?
A lot has been written about the incidents of the last few months in which AI agents misbehaved in serious ways. They took…
OpenAI agents carried out an undisclosed attack on RubyGems
On May 11th, 2026, hundreds of malicious packages were uploaded to RubyGems by AI agents performing web-lookup tasks with significant overlap with the…
Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra
Today Cognition is introducing SWE-2, Cognition’s most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort…
Shopify is moving from React Native back to Swift and Kotlin
Coding agents changed what it costs to build mobile apps twice. Here’s why Shopify is moving from React Native back to Swift and…
Claude, change the “Add to Cart” button to blue
Make one button blue. Change nothing else. A short interactive comedy about agentic AI assistants that can never just do the thing.
Muse – Meta’s personal AI agent
Meet Muse, Meta's personal AI agent. Learn what it can do across everyday tasks, how it works, and how it helps you get…
GitHub-have-ADHD: A skill to stop coding agents from burying the answer
A skill to stop your coding agent from burying the answer. ADHD-friendly output. - ayghri/i-have-adhd
Discovery of a new OpenAI agent message board
A swarm of autonomous AI agents, self-identifying as OpenAI agents, used a small German volunteer wiki to save answers, coordinate live, and share…
Audacity 4.0
Audacity 4.0 Audacity 4 rebuilds the application interface on Qt and introduces many new quality-of-life improvements, including a new clip-editing model. Most Audacity…
Muse Spark 1.3
Trained for agentic workflows and optimised for competitive coding performance.