Does anyone here actually know the underlying theory behind how Transformers or AGI works? I've read many articles on Transformers/GPT-2 and they explain the what they know but none of them can actually explain how any (little own all) of GPT-2 works. To the point where you can explain it to an 8 year old?
It's as if everyone knows a wheel turns, but not why the wheel is rolling. If you are at the bleeding edge, please do bring me up to date by writing a short clear explanation of ex. Transformers/ Bert/ GPT-2, as you won't regret it. It really doesn't take much to write the answers if you know your stuff. I think most can't because they don't know why it works. I'm working on my guide still, may need a week or 2 or more. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T60bb245c0215eb2e-M9df68205dfa7ee9d58a3159c Delivery options: https://agi.topicbox.com/groups/agi/subscription
