Ben Hylak
speaker
402 appearances
2 recordings
1 series
first heard May 2025
last heard 5d ago
Ben Hylak’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Sep 2026 with 1.
Appearances
Like so our customers have to be able to go in there and like define what they're looking for and create this categorizer that can run on millions of messages a day very cheaply.
So that
Yeah.
So um because of a lot of our customers' volumes, like if you think about like play.com or something, like they're just you have millions and millions and millions of requests a day.
So it's not actually feasible at all to send them to an LLM at every request.
Um we can use LLMs like smaller ones, like especially like Gemini Flash, to like do things like summarizing or like describing clusters or stuff like that.
Um as far as actual detection doesn't really work well for that.
So we have a bunch of essentially um
Custom trained embedding models and then models on top of those that are small, like uh they're like technically neural nets, but we can think of them like an SVM or something where they're just like really good at detect doing a first pass detection.
So around like usually ninety-eight percent of the events or nine, it can filter out like ninety-five, ninety-eight percent of the events that are not relevant.
Um, and then kind of the last pass or like is like a small uh
Uh
Uh fine tuned uh LM.
The smallest ones you can do pretty fast.
Umbetting models are like longer.
A lot of it's about having the data, honestly.
Um, having the right data to do it.
And the cool thing is that, um, and I kind of one about when I say like the pipeline's complex, like one of the things I mean is that
Our customer, each of our customers looks pretty different.
What an issue is or is not is pretty different.
Showing 281–300 of 402 · page 15 of 21
← Previous
Next →