I'm using them, but frankly only for things where my quality bar is lower. I've seen little evidence that anyone is routinely getting work that's comparable to competent humans, excepting incredibly recent work like Joshua Rodgers' [0]. And I'll note that even Joshua's work was mainly successful in identifying issues, but actually fixing them involved much more human intervention.

[0] https://joshua.hu/llm-engineer-review-sast-security-ai-tools...