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
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! :)
I am the creator of lightsaber.ml -> a tool for artists to visualize their paintings/art/photographs framed in common places, in a photo-realistic way.
Looking for people to try it out and give me feedback! Reach out to me for access code if you want to try it out :)
Also any advice on where shall I promote the beta-access to get some early users ? Also any advice in general is much appreciated :)
This is exactly my status too right now. I contribute to opensource here and there but apart from that its mostly hacking away at my own libraries, some of which are mildly popular (600stars)