I disagree with some comments saying it's not worth reading since it's generated by LLM. Even though I made it clear that I have download the transcript. LLMs are exceptionally good at generating accurate information if information is directly loaded into context window.

I appreciate the feedback, I did notice that as well and I had this thought perhaps this is not worth fixing since I have a link to tiktokenizer. I decided to remove it and just added a more prominent link to tiktokenizer.

BPE that is used in tokenization is very simple: https://en.wikipedia.org/wiki/Byte-pair_encoding

Update: The "single hard drive" claim was wrong and I've corrected it to "roughly 10 consumer hard drives" (44TB ÷ ~4TB = ~11). Attribution to Karpathy is now a direct link. Added a caveat under the stats noting these are representative 2024-era figures — the exact numbers shift with every release and that's somewhat the point. Also did a few iterations on visual redesign (linked in the header as v2) with a proper top navigation bar after a few people found the dot nav hard to use and UI was jumping.

Also I have not fact checked everything but I have read it and it seems to be aligned with what is described in the lecture.

You're right that it's ultimately just a tool - maybe I'm overthinking it.

Yep I have been trying claude code this week, it works very good so far. Step by step process makes it stand out keeps me in control