[serf]

It's a modeling of language, it's not structurally anything like an LLM.

[mattkrause]

It’s literally a trigram (character) language model. Check any NLP book from before 2015 or so.

LLMs have more stuff bolted onto them (embeddings, RLHF) but the autoregressive core is a direct descendent of that sort of language model.

[justinclift]

So, LM vs LLM? :)

[trollbridge]

It is structurally exactly the same thing as an LLM...