AI doesn't generate working products, that's still your job

Re:AI doesn't generate working products, that's still your job by techpression on Saturday August 01, 2026 @06:47AM (#49133144)

This mirrors my experience too, long term use starts showing incoherence that is impossible to see in isolation.

The funny thing with LLM’s is that with a sufficient sized code base they pretty much will loop forever if you tell them to find and fix issues, making new ones as they fix old ones.

[ Parent | on HN ]

Re:AI doesn't generate working products, that's still your job by amelius on Saturday August 01, 2026 @06:50AM (#49133171)

You have to tell them explicitly not to touch working stuff, and run tests.

[ Parent | on HN ]

Re:AI doesn't generate working products, that's still your job by techpression on Saturday August 01, 2026 @07:42AM (#49133542)

There’s an infinite number of ”working stuff” implementations, which is kind of the problem, bad decisions multiply. That said, looking at small parts of code for improvements tend to work very well for me, optimizing things like data structures, iterations and SQL queries.

I just hope my bank doesn’t go Claude code all the way any time soon.

[ Parent | on HN ]