Hacker News Reader

NLP/Computational Lingustics is NOT a new field. The ACL was founded in 1962

LM research is also old, papers using very shitty LMs (I.e Markov chains) and discussing them have existed since the early 2000s and likely before.

Check yourself before you try to check others.

Try asking a markov chain to think step by step

By definition a Markov chain does everything step by step already, no need to ask!

By that logic, so does a GPT

Parent post is talking about LLMs, i.e. Large LMs. Research on LLMs is indeed in its infancy.