Show HN: Clark Hash, 32x smaller searchable sketches for embeddings

1 points by stan_kirdey a month ago · 0 comments · 1 min read

made a small library using GPT5.5-Pro and autoresearch

you can convert 384-dim f32 vectors go from 1536 bytes to 48 bytes without calibration. works for petabyte scale processing of text in pure online manner.

No comments yet.