If you can just get search time down, and make the summarization a little better, that would be amazing.
For instance, I tried this with 'what Toyotas should I avoid' and it found good relevant videos, but in the summary of 'Bad Toyotas you need to avoid' it misses that certain Toyotas from 2007-2009 had an oil burning issue, which was the main topic of the video. Querying the transcript of the video with 'what Toyotas do I need to avoid' gives a more complete answer. I'm curious how your handling the initial summary.
https://www.questionyoutube.com/
I found myself copy and pasting youtube transcripts into chat to ask questions. This just automates that process, and works on mobile unlike some Chrome Extensions.
[0]https://platform.openai.com/docs/guides/embeddings/embedding...
[1]https://scikit-learn.org/stable/modules/generated/sklearn.me...
I wanted to make it easier to find interesting 10k's, so I made this.
https://ocean-front.vercel.app/
Was thinking about making web app's with guidance but it doesn't support JS yet, so I made a API for myself to consume. Figured I would post it on here as well.
Music LM is really cool. It doesn't like when you ask for a beat in the style of a modern artist though. So I scraped music reviews, and post processed them into prompts.I also added a get random mashup button that can be fun.
https://www.paperswithprompts.com/
Been reading research paper's related to prompting recently and thought it would be nice to have a place to stash them all, so I threw this together last night.
Hi guys. I made an application designed to give what I believe to be the best relationship advice.