How LLMs Work, Explained Without Math – Miguel Grinberg

Re:How LLMs Work, Explained Without Math – Miguel Grinberg by theshrike79 on Monday May 06, 2024 @05:41AM (#40272857)

Yeah, an LLM is not a Markov Chain. The only similarity is that they string words together with weighted possibilities. That's about it.

[ Parent | on HN ]

Re:How LLMs Work, Explained Without Math – Miguel Grinberg by astrange on Monday May 06, 2024 @06:49AM (#40273175)

Well, it is a Markov chain if you do greedy sampling, which 99% of the time you do. So the weird part is why it still works so well.

If you do beam search, RAG, tool usage, etc then the whole system no longer is one.

[ Parent | on HN ]