Illia Polosukhin
speaker
714 appearances
3 recordings
1 series
first heard Oct 2024
last heard Sep 2025
Illia Polosukhin’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
So you kind of like we'll effectively need to create this like environments in which we can verify what AI runs, but I don't think we can like
Like m m m my approach is like I think it's really hard to effectively be a thought police for a even for AI.
But it's way easier to ensure that they don't do anything outside of send the sandbox that violates whatever the rules you apply when you call it.
And so that's kind of uh again, reusing our this verifiable compute, we can actually guarantee that that like as you upload
This model, you can attach effectively set of things that you don't want this model to do, and it can stop it from doing that kind of by running it on the output and verifying if it's correct or not.
So that's kind of the the idea is like to leverage some of that.
And then you still need obviously governance and kind of ways for people to come together and actually decide what it what it is that we don't want, right?
Like for example, probably everybody agrees we don't want bioweapons.
But maybe not everybody agrees on some other things, right?
And so kind of there needs to be some process uh through this.
There I would say we have a bunch of experiments, including actually using AI in the governance.
So you have AI senators effectively, uh like you that people can vote for and then they go and actually make decisions.
And so you kind of because like getting people to vote is hard and g getting people to go and like deep deep research a bunch of stuff to decide how to vote is even harder.
And so you can actually have the deleg delegate
delegates to BAIs as well and you kinda just give them
you know, you vibe with them on like what you think is your opinion and they kinda construct from that their platform.
But you remove this principal agent problem which you have with other people when you v when you
vote them, they still have their own agenda, right?
And so like they may not do what you ask them to do.
So so that's kind of like all the pieces where we're like we're combining all the blockchain and the I side like from different directions and really creating protocols and kind of verifiable compute and privacy and really just you can use it in all those different ways.
Showing 661–680 of 714 · page 34 of 36
← Previous
Next →