A three-tier character encoding that reaches 8,704 characters in two bytes where UTF-8 needs three — with measured savings, the costs, and the reference implementation.
UCE-8 — Unicode 3-byte variable-width Compact Encoding — is a character
encoding sized for the world's living scripts, reaching 128 × 128 × 68 =
1,114,112 characters in at most three bytes.
UTF-8 charges most of the world's living languages three bytes per character.
UCE-8 charges two. This is how it does that, what it measurably saves, and
A 76-character bio, styled once, no longer has one useful length. const s =...
"It works fine on my Mac, but it crashes the moment we hand it to Windows" is a report a lot of...
Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data: The key trick…
A working BPE trainer in about forty lines, then the four things production tokenizers add on top of it.
Frontier-level coding with strong CursorBench results, higher token efficiency, and a faster default variant.
Last week I was profiling a Node.js service that processes large JSON-RPC responses. Three concurrent...
