Haha, I'm one of the authors, although most of the credit goes to the other author (David Fouhey). Despite being in the form of a joke, this sheet is actually functional, for anyone wondering. Like the one in this post, it's inference only, but for a CNN instead of a transformer. I think someone actually made an excel CNN with backpropagation as well.
One possible way of looking at this is that human language is the way most people deal with abstraction, and abstract concepts. And there does seem to be some evidence that some of these abstractions in language may be universal to humans (I don’t fully buy all of the universal grammar stuff but still)
I think you could conceive of abstraction from other forms, maybe something like platonic forms as a base instead of language (again probably not in humans, but in others)
This might be one of the coolest projects I’ve seen recently, are you planning on doing this for smartphones too? Also I wonder how Apple would respond there, just block it like they did Flux?
The YouTube addiction is definitely real... but it's quite sad since mixed in with the entertainment it's one of the best sources in the world for education (video lectures, how tos, etc)
One thing that worked well for me is having two separate profiles, one for educational and one for everything else. That way the education one didn't get as polluted with the most addictive recommendations
(little self-promotion)
One thing I found to be useful was to try to focus on learning more actively, so I built a tool that turns educational videos into mini-courses where it will ask you questions about the content and then use spaced repetition to help you actually remember the information.
One of the other parts is to ensure that the suggestions/feed is focused solely on education, and that you don't fall into the addicting videos trap... (I have the v1 but still working to make this better)
But I think if the addiction is bad enough as in the post, it's probably a better idea to go cold turkey
It's not really giving summaries but gives topic/section timestamps and highlights what was discussed.
(Main focus is actually making mini-courses off of YouTube videos but I found the section summaries really useful for figuring out which parts to watch)
It's not really giving summaries but gives topic/section timestamps and highlights what was discussed
(for example: The Transformer Model (21:06 - 24:48) - Introduction of the Transformer model as a more efficient alternative to recurrent models for language processing)
The main focus is actually creating Anki-like spaced repetition questions/flashcards for videos and lectures you watch to retain knowledge, but I found the section information quite helpful for finding which parts of the video contain the info relating to topics/concepts
You can use GPT-V to create functional components from images directly:
There was an open source project (https://github.com/abi/screenshot-to-code) that I borrowed the prompt from and made a custom GPT for myself where I just drag and drop the image. It’s not perfect but it’s pretty great overall!
