AI coding in a can't-fail distributed storage system

English summary

First-hand: 117 AI-flagged issues each turned into a gtest: 36 confirmed red, 3 refuted, 41 source-only, 37 unverified. AI mapped 11 days of WARN logs (678k lines, 34 call sites) to 5 real defects with 0 false positives; a PR web diff showed about 2% of the real change; multi-agent voting amplified a shared wrong conclusion. AI severity ratings unstable. AI-proposed fixes need review (int truncation). Recommends 4-tier evidence labels.