Binary vector embeddings are so cool (via) Evan Schwartz:
Vector embeddings by themselves are pretty neat. Binary quantized vector embeddings are extra impressive. In short, they can retain 95+% retrieval accuracy with 32x compression and ~25x retrieval speedup.
It's so unintuitive how well this trick works: take a vector of 1024x4 byte floating point numbers (4096 bytes = 32,768 bits), turn that into an array of single bits for > 0 or <= 0 which reduces it to just 1024 bits or 128 bytes - a 1/32 reduction.
Now you can compare vectors using a simple Hamming distance - a count of the number of bits that differ - and yet still get embedding similarity scores that are only around 10% less accurate than if you had used the much larger floating point numbers.
Evan digs into models that this works for, which include OpenAI's text-embedding-3-large
and the small but powerful all-MiniLM-L6-v2
.
Recent articles
- The last six months in LLMs, illustrated by pelicans on bicycles - 6th June 2025
- Tips on prompting ChatGPT for UK technology secretary Peter Kyle - 3rd June 2025
- How often do LLMs snitch? Recreating Theo's SnitchBench with LLM - 31st May 2025