An AI agent reads its own source code, forms a hypothesis for improvement (such as changing a learning rate or an architecture depth), modifies the code, runs the experiment, and evaluates the results ...

Despite widespread industry recommendations, a new ETH Zurich paper concludes that AGENTS.md files may often hinder AI coding agents. The researchers recommend omitting LLM-generated context files ...

OpenAI has launched Codex for Open Source, offering maintainers six months of free ChatGPT Pro and API credits amid a surge of AI-generated pull requests.

Hundreds gathered at ClawCon in New York City to learn about a new wave of powerful personal AI assistants, sizing up both security risks and the lobster spread.