YC's Momentic launches QA-Bench: its AI QA agent finds 2.7x more reproducible bugs than Codex
ycombinator · x · 2026-11-03
Momentic (YC W24) launched on Hacker News and open-sourced QA-Bench, a public benchmark measuring how well AI agents find reproducible bugs in real applications.
- Their AI QA engineer Mo reportedly found 2.7x more reproducible bugs than Codex and 6.3x more than Claude Code (vendor-reported).
- Benchmark methodology and data are public on Hugging Face (momentic/qa-bench), with real bugs, repro steps and severity labels from apps like Gitea.
- The team answered questions all day in the Launch HN thread.
More from coding & agent
- GitHub ships wave of new Copilot features post-Universe, Fusion GA with 30% off — mariorod1 · 2026-11-03
- Laurence Moroney publishes 'Fine-Tuning AI' with O'Reilly, betting on fine-tuning careers — lmoroney · 2026-11-03
- Direct Weight Editing via Codex+Astra Lifts Audio Classifier Accuracy From 84.3% to 88.75% Without Retraining — dansitu · 2026-11-03
- baoyu-design adds Motion: run Claude Design locally with real-time animation editing — dotey · 2026-11-03
- Honest Thumbnails: Chrome extension swaps YouTube clickbait covers for real video frames — jdjohnson · 2026-11-03
- "Who's liable when AI errs?" A delivery engineer on real enterprise AI blockers — 2C_ornot2C · 2026-11-03