GitHub shows whatbroke, a tiny offline diff tool for AI agent behavior
JeffLadish · x · 2026-07-25
- The GitHub screenshot shows the arthi-arumugam-git/whatbroke repository.
- The project description says it can diff an AI agent’s behavior between two runs and show exactly which tool calls, arguments, costs, and outputs changed.
- The visible repo metadata indicates the project is still small and early: 1 contributor, 0 issues, 1 discussion, 2 stars, 0 forks.
Related event: whatbroke: Catching AI Agent Behavior Regressions(2 posts)→
More from coding & agent
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- Stop building agents that can't change models: stable contracts, external state, real evals — rseroter · 2026-10-27
- Cheap models can cost more in agent harnesses than frontier ones, researcher warns — vasuman · 2026-10-27
- Kanzo: A 5k-Line Rust Kanban Binary With MCP for Claude Code and Codex — allmudi · 2026-10-27
- 'A human approves everything' is a trap: approval fatigue and how to actually design safe agents — Efistoffeles · 2026-10-27