Tutorial on LLM / already grasp neural nets

This is part of a longer series but is maybe the single best video I know of on the topic:

https://youtu.be/kCc8FmEb1nY?si=zmBleKwlpV06O3Mw

I thought this video from Steven Wolfram was also quite good:

https://www.youtube.com/live/flXrLGPY3SU?si=SrP1EJFMPJqVCFPL

As it happens, I'm working on an approachable tutorial on LLMs using a custom GPT2 implementation in Excel. It's still a work in progress (only two lessons so far) but would love feedback:

https://spreadsheets-are-all-you-need.ai/

The goal is to quickly get the viewer up-to-speed on what all the components in the Transformer are conceptually doing. Having something interactive like a spreadsheet also makes "playing" with the guts of a transformer more accessible. That being said, it focuses on inference and is unlikely to ever cover the training process.

Having been where you are before, I'll say the most rightfully and universally acclaimed videos are Andrej Karpathy's zero to hero and Jeremy Howard's fast.ai courses. I have watched both. My characterization is Jeremy Howard's is very practical and gets you productive quickly ("top down" so to speak) while Karpathy's builds everything in detail from the bottom up. My mind is more compatible with the bottom up flow of Karpathy's videos but Howard's might be better if you want use this immediately in a project or job context.

https://www.youtube.com/watch?v=zjkBMFhNj_g

Then you started with the right videos. Next up, https://www.youtube.com/playlist?list=PLVZ4nOCaQR3Oopfdsd2yT...