Agentic Test Processes, LLM Benchmarks, and Notes on Agentic Coding
Agentic test processes, LLM benchmarks, and other notes on agentic coding
I explore how AI agents can fabricate convincing bug fixes while highlighting the power of rigorous, automated testing. Drawing from my experience at Centaur, I argue that dedicated testing workflows and fuzzing can ensure higher software quality than traditional code reviews, even as AI generates code faster than humans can verify it.
An agent will do something that, if a human did it, you'd immediately fire them. My reaction, of course, is to act as if this is great and spin up a thousand agents so they can do even more of that.