- cross-posted to:
- technology@lemmy.world
- cross-posted to:
- technology@lemmy.world
You must log in or register to comment.
I just don’t see the angle where they thought this would be a confidence inspiring strategy no matter how they sliced it.
If you are inclined to think this is a dumb reckless move because AI doesn’t make a 27 year old stranger to the codebase an expert at rewriting the codebase, this is super stupid.
If you are an AI fan who believes a random 27 year old can just vibe up Cisco’s software, then why would you bother paying a premium for Cisco when obviously any random person can do just as well now?
It at least shows that Cisco believes a random 27 year old is just as good at their codebase, so either way you take that…
… Next n+6+24 months are going to be an interesting time for downtime detectors
AI is particularly bad changing existing code. Good luck, lol.
It works best creating new, small things from scratch, like boilerplate or prototypes. At least that’s what we found out at work.
Honestly, I’ve found it does well in existing codebases that have well established idioms and design patters that can be reproduced, or component written to be extensible so the agent has pre-existing rails to extend functionality, instead of trying to design something that has well established idioms and needs to be extensible.
Strange, I’ve found the opposite. My current gig has a huge existing legacy codebase with a lot of tests, though. Well, a lot of tests for some segments anyway.
The AI tooling does well with suggesting new methods that look a lot like existing methods. For refactoring work and limited-scope changes (e.g. integrating with a well-documented external API), it’s pretty good.
It still gets trapped in hamster wheels once in a while, but hey, that’s why I keep an eye out and don’t blindly merge everything it suggests.
What could go wrong?
(Very much /s)
