> 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.
If you want to actually learn Korean, check out this site.
[1] An American knowing no Korean moved to Korea and meticulously documented everything he learned, and this website was the result. It's an incredibly thorough study into Korean.
So they put a paper ballot with an RFID chip inside into a machine which then puts your vote into the chip, then you drop the ballot into a box? How is this any different from a regular paper ballot?
It feels a little disingenuous to call it a Recursive Language Model when the recursive depth of the study was only 1.