Hacker News Reader

Unicode bytes are totally bizarro unless you happen to be writing English or some other language with a Latin script. They are absolutely not the best choice.

View on HN

Doesn't really matter for H-Nets. These are Unicode bytes, as you said, so the nets can recover their structure (as demonstrated in the article!).

(I guess the training these could be somewhat more efficient if it was codepoints instead)

Reply on news.ycombinator.com