Re:AI has a deep understanding of how this code works
by ctenb on Tuesday November 25, 2025 @03:37AM
(#46043675)
I agree. It would also work out like a long term supervised learning process though. Humans showing how it's really done, and AI companies taking that as a gold standard for training and development of AI.
Re:AI has a deep understanding of how this code works
by ares623 on Tuesday November 25, 2025 @03:43AM
(#46043718)
I'm not so sure. There's already decades of data available for the existing process.
Re:AI has a deep understanding of how this code works
by ctenb on Tuesday November 25, 2025 @05:31AM
(#46044479)
That is true, but it doesn't help for new languages, frameworks, etc
Re:AI has a deep understanding of how this code works
by jebarker on Tuesday November 25, 2025 @06:57AM
(#46044969)
How would you define “ahead”?
Re:AI has a deep understanding of how this code works
by forgetfulness on Tuesday November 25, 2025 @08:26AM
(#46045580)
Able to make changes preserving correctness over time
Vibecoding reminds me sharply of the height of the Rails hype, products quickly rushed to market off the backs of a slurry of gems and autoimports inserted on generated code, the original authors dipping and teams of maintainers then screeching into a halt
Here the bots will pigheadedly heap one 9000 lines PR onto another, shredding the code base to bits but making it look like a lot of work in the process
Re:AI has a deep understanding of how this code works
by jebarker on Tuesday November 25, 2025 @08:36AM
(#46045650)
Yes, preserving correctness seems like a good metric. My immediate reaction was to think that the parent comment was saying they’d like to see this comparison because AI will come out ahead. On this metric and based on current AI coding it’s hard to see that being the case or even possible to verify.
One path continues on the track it has always been on, human written and maintained.
The other is fully on the AI track. Massive PRs with reviewers rubber stamping them.
I’d love to see which track comes out ahead.
Edit: in fact, perhaps there are open source projects already fully embracing AI authored contributions?