Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
TL;DR Researchers used large language models to iteratively evolve assembly-like programs ("warriors") in the Core War simulation via a process…
Claude Code Emergent Behavior — What Happens When Skills Combine
TL;DR A developer experimenting with a macOS tiling window manager used Claude to combine multiple AI skills and diagnose a…
AI Models Begin Teaching Themselves by Posing Their Own Questions
TL;DR A Wired report describes AI research in which a model appears to improve by generating and answering its own…