Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I think this was something that was waiting for something like LLMs to happen to be solved.

Why aren't AI companies touting "zero-shot"ing huge merge conflicts being resolved by LLMs..



Have you tried this? It would be a nightmare. The LLM wold "solve" the merge conflict by eliminating the code.


But that should make the builds or some tests to fail no? I think we can consider it as a first approximation and proceed to a manual review. It should be a lot easier than manually resolving the difficult merge..


That’s solved by disabling or removing those tests.

I have tried this. It does’t work.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: