Really just instrumentation schemes, I would think.

When you code, do you understand the asm code being built? What are the cache line access patterns? Most software developers have already given up the details of how things work, and lean on tools to handle them.

Which is fine, usually. Depends on what you are doing.

The things that always mattered were the core system, the trunk of a tree if you will. The branches less so, and the leaves not at all (though that is what people see and appreciate! The irony!).

And language does not map to every idea.

The idea of using language for reasoning about protein folding borders on ludicrous. Surely there is latent space more appropriate and (human) language has no expression for it.

Apparently we mostly reuse spatial reasoning and vision lol. I don't know that much about it, though.

I run iCloud private relay and I get very few of their captchas. Actually, I think they are concentrated on just a couple of sites.

There is another project that also converted the go version to rust and got 2x performance like bun did, but will also generate .d.ts files where bun does not.

Edit: found it: https://github.com/tunnckoCoreHQ/tsgolint-rust

Also: bun

Even that one repo is breaking GitHub this week…

I made a harness too, and recently added eval with opencode and pi and I sat between them. No gaming other than trying to figure out why I was really bad on some evals (I was not returning thinking tokens which broke cache, for example, and different model families do things way different here). I have yet to try my harness for coding but I do have a few terabytes for it to read. And I’d rather use a local model that’s fast and good at retention, but that run could take a year, lol.

Sometimes you want both. I wonder if there is a postgresql reranker…

(Tiger data employee fwiw)

We have an alternative full-text search extension as well, pg_textsearch that's completely open source that supports hybrid re-ranking

Here's a blog on it (i linked to the section on hybrid search, there's a code snippet for you in there)

https://www.tigerdata.com/blog/introducing-pg_textsearch-tru...

We're big fans of extending Postgres for more and more usecases

Thanks! I’ll have a look and run some evals.

Oh interesting… I have the entire SEC database to index (only indexing the text in a sliver of it at the moment) and use tsvector and I could use something faster.

That’s only going to work on an MRL embedding.

Also works fairly well for Hadamard-rotated embeddings, as demonstrated here: https://embeddings.info/