Will Bryk

We do post-training of embedding models.

We do RL on search tools, right?

So a lot of these things that are working in LLMs work in retrieval, too, which is kind of interesting.

You don't hear a lot of people talking about it.

So, yeah, in that RL blog post, we just basically try, like a lot of people RL on a search tool, but we haven't seen as many studies testing different search tools yet.

that you are on.

And so we simply RL'd on SERP, so like Google Wrapping versus Exa, and found that, you know, RLing on Exa does way better.

Like, it both, like, uses fewer calls, so it's more efficient, and then it's, like, higher performance.

And this makes sense because, again, like, Exa was designed for agents to use, and so, like, it just...

it just allows agents to make more complex queries.

Like it's really like capture what they actually want as opposed to having like to compress what they want into like shorter phrases that are more for traditional search engines.

So that, that was a cool blog post to explore and think it was really helpful for that.

In general, our research is like the bitter lesson.

So just like scaling laws in lots of different directions.

Some of the ones I mentioned, post-training, pre-training, RL, we've been pretty under the radar.

Like I don't think, uh,

People don't realize how much research we're doing.

We don't publish all of it.

Obviously, we don't publish much of it.

But there is a lot to go and search.