Re:Claude 3.5 Sonnet
by sdwr on Wednesday June 26, 2024 @11:21PM
(#40806867)
Are there any tools out there that expose GPT or Claude to a codebase, and let it write PRs (semi) autonomously?
[ Parent
| on HN ]
Re:Claude 3.5 Sonnet
by CGamesPlay on Wednesday June 26, 2024 @11:31PM
(#40806916)
I know of Sweep <https://docs.sweep.dev>, but honestly the SOTA on SWE-bench, which is basically exactly what you're asking for, is only about a 25% success rate, so expect very mediocre results.
aider is pretty good - https://github.com/paul-gauthier/aider
Thanks, tried it out - it's pretty cheap and pretty good. Being able to commit directly into multiple files simultaneously is great.
It's probably not going to be very good at handling it out of the box. It would require quite a bit of fine tuning.
I’m working on adding Sonnet 3.5 to JACoB this week. So far it’s been very impressive. https://github.com/jacob-ai-bot/jacob
Semi autonomously is the key. Aider and Plandex are both pretty good.
Another one is https://www.github.com/trafficguard/nous which provides a software dev agent that can find/clone repos, create a branch, search in a repo, then delegates to Aider for the code editing in the edit/compile/lint/test loop, and raise a merge request.