"If I had to summarize my position on LLM coding in one sentence, it would be 'Please go read No Silver Bullet'. I think Brooks’ argument there is both theoretically correct and validated by empirical results, and sets some pretty strong limits on the impact LLM coding, or any other tool or technique which solely or primarily attacks accidental difficulty, can have."

@ubernostrum, 2026

https://www.b-list.org/weblog/2026/apr/09/llms/

#MOLE #AI #LLM #VibeCoding #AutogeneratedCode