Post #2430899
2026-05-06 16:55 UTC
What was then described sounded more like what a business analyst might do. Look at business requirements. Prompt an LLM to bullet-point the changes. Examine tests to see if "they make sense". And somehow make assessments that the code is secure and performant?
I complained that asking an LLM to review LLM generated code is redundant, and that we are making our work redundant based on the belief that the LLMs are fully capable of delivering product with little human intervention. Someone on the team mentioned that we would be spending less time coding and doing more "engineering"...
... at which point I just sort of gave up... lol... engineering? Naaah...
Needless to say, "fun" start to the morning.
2/2
Replies (1)
-
@goatcheese@eldritch.cafe 2026-05-06 17:49
@pythonbynight@hachyderm.io some people at my company are also pushing for broader LLM use while trying to "find solutions to the code review problem". I was thinking a few days ago, they sound like they're too embarrassed to say "let's get rid of reviews entirely". Like they're hoping someone else will suggest it. Or that the practice will disappear organically. Clown engineering 🤡