I'm building https://www.themoonlight.io/en with a small team of four - it
s an AI aided PDF reader, designed to make research papers more accessible :)
Lately, I've seen a growing interest in academic content from non-researchers, so I'm focusing on features like automatic summarization and LaTeX math explanation to lower the barrier. I hope this helps more people engage with research and ultimately push global innovation forward.
True. tried manually reviewing all papers on arxiv under cs.cl for a year and a half and really felt the need to automate this
https://corca.substack.com/
Tried to with vector embeddings and stuff and worked out okay-ish but sadly failed to get a solid mvp. Some retro tldr:
1. Fomo of losing papers not looked over by a proper researcher
2. What is a good, novel paper - research undoubtedly has its trends and cold start problem, inevitably fueling papers with overused topics to be tagged noteworthy, negating the purpose of doing daily arxiv digest
Lately, I've seen a growing interest in academic content from non-researchers, so I'm focusing on features like automatic summarization and LaTeX math explanation to lower the barrier. I hope this helps more people engage with research and ultimately push global innovation forward.
If anyone is interested, here's a quick 1 minute demo: https://www.youtube.com/watch?v=L1i8Yp_APbg Feedback is always welcome!