Adding verification and accountability to coding agents: 6 auto-checked claims, 455/455 tests pass
jasonkneen · x · 2026-11-22
Jason Kneen shared before/after screenshots showing what adding verification and accountability to a coding agent harness does: initially 1 of 6 agent claims fails (expected function text not found in app.rs) and triggers correction; the final report shows 455/455 cargo tests passing, a zero-warning build, a clean commit, and all 6 claims verified. The core technique is turning each agent claim into machine-checkable exists/contains/cmdok assertions that auto-correct on failure.
More from coding & agent
- MIT study: coding agents boost commits 240% but releases only 30% — apps ship into the void — GaryMarcus · 2026-11-22
- gemini-cli PR fixes ACP mode hanging on initialize when sandbox is enabled — Raamia · 2026-11-22
- Open-Source Free PBR Material Generator Built on Apple Depth Pro 2 — joemeno · 2026-11-22
- Open-source coding agent control plane T3 Code claims 500K+ devs orchestrating Claude Code, Codex and more — churchkey · 2026-11-22
- prime-rl 0.11.0 ships: 1.5x faster training, new pretraining entrypoint, Mega MoE dispatcher — samsja19 · 2026-11-22
- AI computer use mocked as 'tentacle barrel' self-driving: screenshots to GPU cluster just to move a cursor — ZeroStateReflex · 2026-11-22