I am still confused if vector size should be 1024 or 728 lol.
This is where good judgement comes in, which is difficult to encode rules for.
Indeed. Amazon originally advertised CodeGuru as being "like having a distinguished engineer on call, 24x7".[^1] That became a punchline at work for a good while.
I can definitely see the value of a tool that helps identify issues and suggest fixes for stuff beyond your typical linter, though. In theory, getting that stuff out of the way could make for more meaningful human reviews. (Just don't overpromise what it can reasonably do.)
[^1]: https://web.archive.org/web/20191203185853/https://aws.amazo...
One of our largest learnings is that state of the art LLM's aren't good enough to write code autonomously, but they are good enough to be helpful during code review.
Would love to get your thoughts on sweep. Does it meet your expectations? If not, where does it fall short?
It’s not perfect even after that but gives me a good starting point and often just needs a minor change.
Take a look at this PR for example: https://github.com/julep-ai/julep/pull/311
Ellipsis caught a bunch of things that would have come up only in code review later. It also got a few things wrong but they are easy to ignore. I like it overall, helpful once you get the hang of it although far from a “junior dev”.