Oh, wow. I wasn't aware that binary quantization was being applied to embeddings! And the code search related use cases were very helpful for grokking when quantization is OK versus when more precision must be maintained. So they sound bearish on Matryoshka? Post makes it sound like Air Context never reduces dimensions.
Thanks, authors. Please follow through on the rest of the series. I learned a bunch.
kaycebasques · · focus · HN ↗
Thanks, authors. Please follow through on the rest of the series. I learned a bunch.