Bluesky Answer Search
Answers quoted word for word from the last 100,000 posts of the
Artificial (and real) Intelligence list, kept live and searched on your GPU.
Nothing downloaded yet. The first search fetches about 38 MB, which the browser then keeps.
Settings
How it works
Ettin-17m turns your query into a vector and your GPU searches the posts
for the closest ones. Then Ettin scores every sentence of those posts against the query, and the best sentence from
each of the top posts is shown, best match first. Nothing is generated, so nothing can be misquoted.
| part | MB over the wire |
|---|
| Ettin-17m embedder, int4 token table, and its tokenizer | 10.5 |
| Index: 100,000 posts as 2-bit codes (768 dimensions each) | 20.0 |
| The posts' text, gzipped | 7.1 |
| The tokenizer library and the WebGPU engines for Ettin and the scan | 0.2 |
| total | 37.8 |
|---|
Model and engines measured 2026-11-03 with compression on; the index sizes are today's snapshot.
A GitHub Action rebuilds the snapshot every morning: it asks Bluesky for the list's new posts, embeds them with the same
Ettin model, and drops the oldest beyond 100,000. This tab then asks Bluesky's public API for the posts written since the
snapshot, embeds them on your GPU, adds them to the same index, and checks for new ones every minute while the tab is
visible. Your browser keeps a snapshot for two days and fills in the gap itself, so a daily visitor downloads the index
every other day. Your query and the results never leave this tab; the only requests after the download
are those for new posts.