Nathan Lambert
speaker
1,013 appearances
1 recordings
1 series
first heard Nov 2024
last heard Nov 2024
Nathan Lambert’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
thing that you are feeling where it just doesn't it doesn't seem like as a
open research area, we have gotten to the bottom of what human or like what preference data is doing to the models and like why we can just not use humans.
So I got like I'm like, oh, this sucks.
But I I do think eventually
We will continue to
chip away at that understanding.
Which goes back to this like humans, high noise, low bias, machines, low noise, high bias.
Like eventually we will understand what these biases and noises
represent but we do not.
And I'm
It's fine.
I think RLHF has shifted more away from this like safety or like what is a preference area that's not discussed as much now.
Which I think
when you're talking about normative relations and kind of these sociological things in
quote unquote, preference tuning.
it is more important to be in touch with these types of like human versus machine biases.
If it's literally like make math number go up, I'm like, okay, like it's it's fine to not have as clear of a
a guidance there.
I think like the thing that I've wanted to see is you give it instructions to annotators.
And I would like to see how well the model reflects the instructions given.
Showing 781–800 of 1,013 · page 40 of 51
← Previous
Next →