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
Okay, let's let's push on from technological determinism and talk about this research research agenda that you've been involved in, I guess, promoting and elaborating called uh cooperative AI.
I mean, yeah, as we've been saying, uh the the main focus, I suppose, of differential technological development uh thinking with regards to AI has has been alignment for for many, many years.
But uh but you and some co-authors in this paper back in 2021 said this there's this whole other cluster of behaviors that we might like to speed up the development of around cooperation that you think
could be similarly important, or at least on the margin, could be similarly important because n people aren't really talking or or thinking about it.
Wha how how do you define cooperative AI and and why do you think it's it's quite key?
Okay.
So the the idea is even if you have AIs that are aligned with the goals of their uh operators, then this doesn't necessarily lead to a good outcome if those operators are in conflict with one another.
That the the AI systems that they're that they're working with could simply lead you to a disastrous outcome, just as the fact that we're maybe aligned with our own interests doesn't necessarily produce a great outcome across humanity as a whole.
You can still end up in in traps and um an unintended disaster.
masters.
And and the same basically applies in a world where where it's AGI that's doing most of the operationalization of what people want.
Yeah.
I guess a s a specter that haunts this um entire conversation, if we're if we're focusing on the on on the military case in particular, is that I guess h historically when you have countries that are in intense conflict with one another, you get this process of brinksmanship where, you know, a one country will escalate and the other country has to decide whether to like, you know, uh cool or like escalate or or back down.
Um and kind of you you keep getting this brinksmanship escalation process until I guess at some point uh one of them uh blinks or th or they decide to find some solution that that that that makes them both happy.
Trouble is if you have an AI operated military, these AIs can make these decisions on a completely inhuman timescale, where this entire process of brinksmanship that might take days or weeks or months uh when when humans are the ones who have to go away to a meeting and think about it and discuss it and decide uh how to react.
It could all all play out in a matter of minutes, basically.
And I think that that that possibility terrifies people and and and and is one thing that is discouraging people, I guess, from from uh placing AI into important decision making roles and uh you know over national security at all.
So
Lo looking over this paper, I I wasn't initially completely convinced that this was something that we had to go far out of our way to to focus on, but basically because
I think of cooperative behavior and knowing how to cooperate with other agents as just something that's um instrumentally convergently useful.
Showing 761–780 of 1,787 · page 39 of 90
← Previous
Next →