For teams actively using AI coding assistants (Copilot, Cursor, Windsurf, etc.), I'm noticing a frustrating pattern: the more complex your codebase, the more time developers spend preventing AI from breaking things.
Some common scenarios I keep running into:
* AI suggests code that completely ignores existing patterns
* It recreates components we already have
* It modifies core architecture without understanding implications
* It forgets critical context from previous conversations
* It needs constant reminders about our tech stack decisions
For engineering teams using AI tools:
1. How often do you catch AI trying to make breaking changes?
2. How much time do you spend reviewing/correcting AI suggestions?
3. What workflows have you developed to prevent AI from going off track?
Particularly interested in experiences from teams with mature codebases.
Comments URL: https://news.ycombinator.com/item?id=42701745
Points: 16
# Comments: 14
Accedi per aggiungere un commento
Altri post in questo gruppo
Article URL: https://www.cpubenchmark.net/year-on-year.html
I've wanted to make my own OS since I started programming. Now, 5 years later, I did it (kind of).
Sure, it is really basic, has very little functionality, but I made it and I'm proud of that. O
Article URL: https://arxiv.org/abs/2502.07577
Comments URL: https://news.ycombinator.c
Article URL: https://imapsync.lamiral.info/
Comments URL: https://news.ycombinator.com/i
Article URL: https://restofworld.org/2025/syria-international-tech-conference-sync-25/
Comments URL:
