G github.com Show HN: Clark Hash, 32x smaller searchable sketches for embeddings made a small library using GPT5.5-Pro and autoresearchyou 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. 1 points stan_kirdey 5 months ago 0 comments
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.