Rob Wiblin
speaker
1,787 appearances
3 recordings
1 series
first heard Sep 2024
last heard May 2025
Rob Wiblin’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
That if you're developing agents that are just good at their job at all, that are in fact useful to apply, then they have to learn how to cooperate, at least in the kind of cases where they're being used, because otherwise they're just bad at their job.
It's the kind of thing like we were talking about earlier, that there's a lot of commercial pressure to develop this.
And also these models we're we're imagining are like very generally capable.
are they're yeah, you know, insightful, intelligent, uh maybe maybe approaching or exceeding human level.
Why wouldn't they just be able to think about these things and figure out how to cooperate the same way that I think, you know, our thoughtful human beings figure out how to tr try to avoid conflict as as best they can?
I guess yeah, well we've talked about the the military issues with cooperation, but uh that's like a pretty extreme case.
And imagine there's a a lot more other more mundane examples where cooperation could be useful.
Did do you wanna give a g give a couple of those?
Yeah.
There's other ways that I thought it might be easier for AIs to corporate than it is for humans.
I mean, one one thing is that they they just have a much higher bandwidth com of communication.
Uh they can basically just like send an enormous number of words, have a very lengthy conversation where humans just wouldn't regard it as worth it in order to to try to try to reach some some some bargaining outcome.
I guess also you can kind of they can commit to act in a particular way because you can just copy them and demonstrate that in a given situation.
uh a a model will will uh will accept a particular kind of bargain con consistently and then say, well, so all of the exact copies of this piece of software will do the same thing, right?
So I've I've created this cooperative um software and and and and you should and you should trust me.
That's not something that you can easily do with human beings.
I guess we try to look at their historical track record to learn what they're like.
But here it's even easier to get to to judge the the character of an AI model.
Are are there ways that uh important ways that it could be more difficult or that it's like less straightforward for
for AAs to to cooperate with one another than humans?
Showing 781–800 of 1,787 · page 40 of 90
← Previous
Next →