A composite measure of consequential decision-making by AI across 9 domains

Analyses of large-scale Claude Code agent behavior

Overlap analysis, boundary testing, and metacognitive scoring for LLM coding agents

Terminal dashboard for navigating, searching, and monitoring Claude Code activity

Specification for autonomous agent software construction

AI-native development environment for macOS with multi-agent orchestration

Daily curated papers on agentic AI, context/memory, recursive learning, and long-horizon software dev

Research briefs on artificial intelligence policy, infrastructure, and industry dynamics

Graphics playground reimagining the Atari ST GEM desktop with p5.js

Editorial rulebook for cleaning up AI-drafted prose: cadence antipatterns, fixes, and a downloadable style guide