9 Comments
User's avatar
Vishal Poduval's avatar

How good is this 👏 Thanks a ton Shivani! Can't wait for the next one.

Ashish Pratap Singh's avatar

Excellent breakdown of how foundational LLMs are trained. Super well-explained.

Great work Shivani!

Shivani Virdi's avatar

Thanks a ton, Ashish! Also I’d love feedback on how easy/difficult was this to comprehend, read and create mental models!

Ashish Pratap Singh's avatar

Overall, I found this blog beginner-friendly, well-structured and easy to follow.

You might consider adding references or links for technical terms like backpropagation, BPE, or Transformers, as some readers may not be familiar with them.

This is just based on my experience, but here are a few alternate title suggestions you could consider for this blog:

- How LLMs Are Trained (Step-by-Step)

- An Inside Look at How LLMs Are Trained

- How Does GPT Learn? A Beginner-Friendly Guide

The goal is to keep it simple, make it widely appealing while also being accurate since the title plays a big role in driving clicks and reads.

Overall, a great start for your newsletter, kudos!

Shivani Virdi's avatar

This is extremely valuable Ashish, thanks so much! Noted 😊🙌🏻

Jigneah Sanghvi's avatar

I think this is by far the best explanation of LLM for non technical person. Thank you Shivani.

Shubham Jain's avatar

Nicely explained. And adding those resources at end is a good move.

Luq's avatar

Brilliant article Shivani 👏👏… cant wait for part2

Jagadish Thadakamalla's avatar

This is super cool , Shivani. Feel

Like it’s TL;DR, but definitely worth reading .