Chuck Kwong

speaker

111 appearances 1 recordings 1 series first heard Jul 2026 last heard 20 Jul

Chuck Kwong’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

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

newest first · ▶ plays the moment

But the key difference is that they're all user driven.

I guess the question is like how do how

think about all the different evals and how you differentiate between each type.

I think one way to look at it is is like who who's doing the judging of these evals?

Is it the user?

Is it a trained annotator or expert?

Uh or is it a machine, like another L M, right?

And s and also what what kind of domain expertise they bring to that judgment.

Um that's kind of how you can think about evals in between those two dimensions, there's like different types.

So users.

are judging their own outputs and they bring their own expertise.

They are the ones that that know their situations the best.

They know their own prompts.

They know their own intent.

Why they bring that question.

for machine emouse, the the judge is another LOM.

And the the expertise is all the sort of the collective team that helped build that classifier and that rubric and that kind of lives in that L O M.

The third one is the sort of a third party judge.

And those could be separate experts in their own domain.

It could be uh programmers, it could be literature professors judging types of AI outputs.

Showing 41–60 of 111 · page 3 of 6