ngrok.io url does not spark confidence, this seems to just be a openai frontend also the "arxiv.org" restriction is only applied on frontend so it'll gladly go download any file (I tried with a 1gb file and it seems like it might've broke the entire thing since it keeps throwing Internal Server Error).
This looks pretty interesting! But the landing page has only one sentence : Understand and implement research papers faster, followed by a get in touch button. Care to extrapolate more? The blog button doesn't work as well?
Thanks for checking it out. We are trying to build a system for engineers, researchers, academics, basically anyone who has to implement cutting research into computer code for their product. Usually the process of finding the right paper, and then understanding it, and then implementing it in computer code is very time consuming, and our hypothesis is that we can reduce that time drastically by using large language models. We are still very early and exploring the right problem-solution fit and feedback from early testers like you is extremely valuable! so thanks for reaching out! join our discord! :)
you are correct, its supposed to generate code for things that are discussed in the paper. the app starts with an example paper, but you can give it any arxiv link. it works best when the task you tell it to implement is actually discussed in the paper, or else it will hallucinate random things. its no where near good as of now but we are constantly improving it
hmm that's weird. did you make sure that you typed "implement: <task>" ? it has to be in that exact format for it to generate code. we're gonna make this experience much better soon
12 comments
[ 3.7 ms ] story [ 48.1 ms ] threadIs it usually supposed to take the paper as context and the generate code?