Bug Hunt Bench author says his code-review skill significantly lifts model scores
PawelHuryn · x · 2026-09-24
Pawel Huryn says his code-review skill measurably improves model scores on his Bug Hunt Bench (105 planted bugs across two real repos), and nothing in it is benchmark-specific, though full numbers aren't published yet. The skill is part of the open-source pm-ai-shipping kit (26.6k stars): it documents vibe-coded apps, then audits the gap between documented intent and actual code—catching correctness, security, and performance defects that generic scanners miss.
More from coding & agent
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12
- Building an End-to-End Hedge Fund in Python with Claude Code: A 5-Step Workflow — mdancho84 · 2026-11-12
- Jeff Dean: comfortable with engineers spending up to $10M/year on AI tools — deedydas · 2026-11-12
- Developer builds VladOS, a personal life dashboard, by just describing it to an AI agent — haltakov · 2026-11-12