21–30 of 87 posts
Does this differ from GitHub's CoPilot in any user-noticeable way? (outside of the platform it's available on)
One thing I noticed is it seems to have an "Explain code" feature, giving you a textual explanation of a block of code you select, which I'm not aware of GitHub having.
ref: https://github.blog/2022-09-14-8-things-you-didnt-know-you-c...
replit employee here. the team who built this is very small (less than a dozen, including non-eng roles for the go to market), and went from idea to general availability in 8 weeks
That's very impressive. Hats off to them! I dont think this is too out of the ordinary either though. I'd guess they started off with a LLM from hugging face, set up some pipeline to ingest code from replit repos to finetune the LLM. The ML aspect of this is not terribly hard given that they probably dont need to train a LLM from scratch. Figuring out how store and serve from replit repos (or publicly available code…
iirc the team managed to bring it to a lever an order of magnitude lower than off-the-shelf models
Does this differ from GitHub's CoPilot in any user-noticeable way? (outside of the platform it's available on)
One thing I noticed is it seems to have an "Explain code" feature, giving you a textual explanation of a block of code you select, which I'm not aware of GitHub having.
replit employee here. the team who built this is very small (less than a dozen, including non-eng roles for the go to market), and went from idea to general availability in 8 weeks
replit employee here. the team who built this is very small (less than a dozen, including non-eng roles for the go to market), and went from idea to general availability in 8 weeks
That's very impressive. Hats off to them! I dont think this is too out of the ordinary either though. I'd guess they started off with a LLM from hugging face, set up some pipeline to ingest code from replit repos to finetune the LLM. The ML aspect of this is not terribly hard given that they probably dont need to train a LLM from scratch. Figuring out how store and serve from replit repos (or publicly available code…
I think it's also a bit scary, because 8 weeks is very little time for testing, tuning, and validation of something as opaque as a machine learning model. If it worked right the first time, that's great. But there is still a lot of inherent uncertainty in ML projects. Decision makers need to take that uncertainty into account when planning.
That, or, the 8 weeks only covers the final training runs and the implementation/deployment, and doesn't include time spent developing and tuning proof-of-concept prototype models.
> trained on publicly available code Fully respecting the licenses this code was published under, one would hope?
For a simpler example than code-generating ML, if I write a program to recognize a directory of source code vs non-source code, and my logic is if (unbalanced parenthesis count in all files > X) { return "not source code"; } else { return "source code"}.
And then I compute X by scanning over the linux kernel source and counting the amount of unbalanced parens, have I just committed a GPL violation if I don't GPL my source code recognizer?
replit employee here. the team who built this is very small (less than a dozen, including non-eng roles for the go to market), and went from idea to general availability in 8 weeks
any interns on that team who are going to get bullied by replits lawyers in the near future?