News for hackers. Stuff that matters.
Re:Arthur Whitney releases an open-source K with MIT license by eigenvalue on Saturday June 01, 2024 @07:04AM (#40544636)
I suppose in our new world of LLMs, using as few tokens as possible means you can cram more in a small context window, which could be helpful in various ways.
Re:Arthur Whitney releases an open-source K with MIT license by 082349872349872 on Saturday June 01, 2024 @07:19AM (#40544739)
Maybe someone could produce an LLM which takes a line of vector language code and expands it into the dozen(s) of lines of equivalent pseudo-algol?

(I mean, you could skip the whole hallucination thing and write an exact converter, but that'd be a lot of effort for code that'd probably get used about as much as M-expression to S-expression converters do in the lisp world?)

Re:Arthur Whitney releases an open-source K with MIT license by eggy on Saturday June 01, 2024 @08:15AM (#40545099)
There are a few articles of using J or APL for ANNs and CNNs out there. Here's one:

  https://arxiv.org/pdf/1912.05234