Jesse Zhang

speaker
452 appearances 1 recordings 1 series first heard Jul 2026 last heard 31 Jul

Jesse Zhang’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months
1 · Jul OctJan 26AprJulnow

Recordings per month over the last 12 months — 1 in all, peaking in Jul 2026 with 1.

Appearances

newest first · ▶ plays the moment
So today, 90% of our workflow is on open source.
And again, the main reason was for latency to really optimize our voice agents.
And I think we've just over the last year, we've seen tremendous improvement in how it sounds, how it feels, but it's still also like keeping the accuracy high.
And then the remaining 10%, of course, we're still using the closed source models and the frontier models for a lot of new projects or new products.
And I think that's just where the industry is moving to.
So if you kind of were to generalize this, every model, you can kind of evaluate along three dimensions.
It's costs, intelligence, and latency.
And depending on what you need, you want to kind of be at the limit of those three.
And sometimes you can trade off, right?
So in our case, we knew that we actually pulled back on intelligence because all I had to do was that one task.
But now we get these latency advantages.
Yeah, I think they'll get there, but it'll probably take longer than people think.
Because even with our team, fine-tuning these models is non-trivial.
It's not just, oh, you can...
It's like, all right, we made a decision to use open source.
Let's just use open source.
Like you have to get the data.
And then more importantly, you have to like have good evals.
And if you think about our evals, right, our evals are very specific to us.
You can't just like use some public eval set and like that just does the job.
Showing 41–60 of 452 · page 3 of 23 ← Previous Next →