News for hackers. Stuff that matters.

A comment on AI usage generates a fragile codebase.

Re:AI usage generates a fragile codebase by retrac98 on Tuesday November 10, 2026 @06:51AM (#50439005)
My experience has been sort of the opposite. In the past 6 months I don’t think I’ve introduced a single production bug through my work, which is unheard of (for me, at least).

LLM code is verbose, and often quite inflexible, but that rigidity and verbosity tends to come from the AI being very thorough about ensuring the code does exactly what’s expected, and it seems to leave much less room for error as a result. It acts as a really good forcing function for specificity on requirements, and for thinking through "what if" scenarios.

[ Parent | on HN ]
Re:AI usage generates a fragile codebase by pamcake on Tuesday November 10, 2026 @07:01AM (#50439095)
in order to make sense of this comment it would help to know what kind of codebase(s) you are referring to like what language and application(s).
[ Parent | on HN ]
Re:AI usage generates a fragile codebase by retrac98 on Tuesday November 10, 2026 @08:10AM (#50439811)
In this instance, a monolithic rails API for a series of iOS apps with a few million daily active users. But I also work on some other TypeScript projects and have felt similar benefits there.
[ Parent | on HN ]
Re:AI usage generates a fragile codebase by soon_to_be_sb on Tuesday November 10, 2026 @12:05PM (#50443123)
> tends to come from the AI being very thorough about ensuring the code does exactly what’s expected..

So terse and flexible code can't be made to do exactly what is expected?

[ Parent | on HN ]