@goyalayus: Actually, you don't need any of these but just these four books, then you can go into any niche and pick up things. (I …

X AI KOLs Timeline News

Summary

A tweet from @goyalayus suggests that four unspecified books are sufficient to learn any niche, followed by a quoted recommendation from Praveen Kumar Verma to read foundational LLM papers in a specific order, including Attention Is All You Need, BERT, GPT, GPT-2, Scaling Laws, and GPT-3.

Actually, you don't need any of these but just these four books, then you can go into any niche and pick up things. (I don't know any good sources for parallel programming, but yeah, that book, too. Also, I assume you need to know basic calculus and matrices) https://t.co/Qqnkigl4Na
Original Article
View Cached Full Text

Cached at: 07/05/26, 12:35 PM

Actually, you don’t need any of these but just these four books, then you can go into any niche and pick up things.

(I don’t know any good sources for parallel programming, but yeah, that book, too. Also, I assume you need to know basic calculus and matrices) https://t.co/Qqnkigl4Na

Praveen Kumar Verma (@Alacritic_Super): If you want to actually understand LLMs, read these papers in order:

  1. Attention Is All You Need (Transformers)
  2. BERT
  3. GPT (Improving Language Understanding by Generative Pre-Training)
  4. GPT-2 (Scaling + Zero-Shot)
  5. Scaling Laws for Neural Language Models
  6. GPT-3

Similar Articles