[Xyra]

Exactly, people want precision and control sometimes. Also it's very hard to beat SQL query planners when you have lots of material views and indexes. Like this is a lot more powerful for most use cases for exploring these documents than if you just had all these documents as json on your local machine and could write whatever python you wanted.

Yeah I've out a lot of care into rate-limiting and security. We do AST parsing and block certain joins, and Hacker News has not bricked or overloaded my machine yet--there's actually a lot more bandwidth for people to run expensive queries.

As for getting good semantic queries for different domains, one thing Claude can do besides use our embed endpoint to embed arbitrary text as a search vector, is use compositions of centroids (averages) of vectors in our database, as search vectors. Like it can effortlessly average every lesswrong chunk embedding over text mentioning "optimization" and search with that. You can actually ask Claude to run an experiment averaging the "optimization" vectors from different sources, and see what kind of different queries you get when using them on different sources. Then the fun challenge would be figuring out legible vectors that bridge the gap between these different platform's vectors. Maybe there's half the cosine distance when you average the lesswrong "optimization" vector with embed("convex/nonconvex optimization, SGD, loss landscapes, constrained optimization.")

[kiney]

if performance becomes a problem statically hosting sqlite DBs with client side queries and http range requests is an interesting approach:

https://github.com/phiresky/sql.js-httpvfs

[Xyra]

Thanks, that's very interesting.

[plagiarist]

That's a neat thought. What's the granularity of the text getting embedded? I assume that makes a large difference in what the average vector ends up representing?

[Xyra]

~300 token chunks right now. Have other exciting embedding strategies in the works.