Dev.to · Baessi
🧠 Large Language Models
⚡ AI Lesson
2mo ago
6 months solo on a multi-agent PR reviewer. 10.93 vs 3.80 blockers/PR (claude alone) on my benchmark — please test on real PRs and tell me where it's wrong
TL;DR: I built a 3-LLM code reviewer (Claude + GPT-5 + Gemini that deliberate). My synthetic-bug...