Why not just use an eval harness to prove this catches more real bugs? Benchmarks on actual bug classes would be far more convincing than comparing against /review.
2 karma · joined April 28, 2026
Honestly, I kind of forgot the name because of the LLM rush and everything around, but this is so good. Coming across brought back a lot of memories. Thank you for that, and yes, I will check out the entire project. It looks good.