Hacker Timesnew | past | comments | ask | show | jobs | submitlogin

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.



So, LM vs LLM? :)




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: