Sander Schulhoff
speaker
947 appearances
1 recordings
1 series
first heard Jun 2025
last heard Jun 2025
Sander Schulhoff’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
You know, it's funny, I the more I get into prompting techniques, the less I remember about classical uh ML.
Uh but if you know like uh random forests, uh these are uh a kind of a more classical form
Of ensembling techniques.
So, anyways, a specific example of one of these techniques is called Mixture of Reasoning Experts, which is or was developed by a colleague of mine who's currently at Stanford.
And the idea here is you have some question, it could be a math question, it could really be any question.
And you get yourself together a set of experts.
experts.
And these are basically different LLMs or LLMs prompted in different ways, where some of them might even have access to the internet or other databases.
And so you might a ask them like, I don't know, how many trophies does Real Madrid have?
And you might say to one of them, okay, you need to act as an English professor and answer this question.
Uh and then another one like, you need to act as a soccer historian and answer this question.
Uh and then you might give a third one no role but just like access to the internet or something like that.
Uh and so you think kind of, all right, like the soccer historian guy, uh, and the Internet search one say they give back
I don't know, like 13, and the the English professor is like four.
So you take 13 as your final response.
And one of the neat things about well, roles as we discussed before, which may or may not work, is that they can kind of activate different regions of the model's neural brain and make it perform differently and better or worse on some tasks.
So if you have a bunch of different models,
models you're asking, and then you take the final result or the most common result as your final result, you can often get better performance overall.
It
be different models.
Showing 381–400 of 947 · page 20 of 48
← Previous
Next →