Comment

Comment by akomtu

What prevents parallel LLM training? If you read book 1 first and then book 2, the resulting update in your knowledge will be the same if you read the books in the reverse order. It seems reasonable to assume that LLM is trained on each book independently, the two deltas in the LLM weights can be just added up.
parent akomtu 3 years ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton