Systems and ML, mostly where the two meet.https://adervark.com/https://adervark.com/writing/the-headline-is-a-tokeniser/https://adervark.com/writing/the-headline-is-a-tokeniser/How the homepage trains a byte-level BPE vocabulary in your browser, using the page's own text as the corpus.Tue, 03 Nov 2026 00:00:00 GMT