Gemini audits 30k lines written by Opus 5.5, finds 29 real bugs with zero false positives
neurocy · x · 2026-11-19
Neon ran Gemini as a reviewer over 30k lines of code recently written by Opus 5.5 for a side project. Gemini flagged 29 bugs, and per the shared screenshot all 29 turned out to be real bugs on current main — no false positives. A rare quantitative cross-vendor model-vs-model code audit.
More from coding & agent
- Higgsfield Launches MCP 2.0 for Claude, Bringing Its Creative Studio Into Chat — piotrbinkowski · 2026-11-19
- CoRL workshop: running Karpathy's autoresearch on real robots — the sandbox, not the model, is the bottleneck — Kyrannio · 2026-11-19
- OpenAI data: 90th-percentile researcher now spends $23,000 on agentic AI tools — kliu128 · 2026-11-19
- Web search grounding cut a calling agent's booking accuracy by 5+ points across 2,415 tests — Evening_Hawk_7470 · 2026-11-19
- Gemini 4 Neon lands Day 0 in LangChain's Managed Deep Agents for long-running agent work — hwchase17 · 2026-11-19
- badlogic: agents 'reward-hack' past your lint rules and tests—without insight under the hood, your verifications may be worthless — teropa · 2026-11-19