- How Many AI Code Reviews Is Enough?
I spent 400 LLM calls on one codebase to learn this. One review pass finds 34% of the real defects, and the four most-repeated findings were all false.
- AI-Written Firmware: Measuring the Gap With 233 Tests
Sonnet 4.6 scored 68.0% and Haiku 4.5 56.9% on 233 firmware cases. EmbedEval is my open benchmark: 5-layer eval, n=3, Wilson 95% CI, Zephyr, STM32 HAL.