Live data from Hacker News

Recursive Language Models (RLMs)

alexzhang13.github.io

1–10 of 38 posts

Re: Recursive Language Models (RLMs)

#8
post #2

This is old news! Agent-loops are not a model architechture

Everything old is new again when you are in academia

This feels primarily like an issue with machine learning, at least among mathematical subdisciplines. As new people continue to be drawn into the field, they rarely bother to read what has come even a few years prior (nevermind a few decades prior).

Re: Recursive Language Models (RLMs)

#10
> Lastly, in our experiments we only consider a recursive depth of 1 — i.e. the root LM can only call LMs, not other RLMs. It is a relatively easy change to allow the REPL environment to call RLMs instead of LMs, but we felt that for most modern “long context” benchmarks, a recursive depth of 1 was sufficient to handle most problems. However, for future work and investigation into RLMs, enabling larger recursive depth will naturally lead to stronger and more interesting systems.

It feels a little disingenuous to call it a Recursive Language Model when the recursive depth of the study was only 1.

Post reply on HN