Jul 26, 2022 · 2 hr 15 min · 31 segments
Oriol Vinyals is the Research Director and Deep Learning Lead at DeepMind. Please support this podcast by checking out our sponsors: – **Shopify**: https://shopify.com/lex to get 14-day free trial…
Oriol VinyalsGuest[gentle music] You are one of the most brilliant researchers in the history of AI, working across all kinds of modalities.
Uh, so then we're talking about languages, images, even biology, and, uh, games, as we talked about last time.
In your lifetime, will we be able to build an AI system that's able to replace me as the interviewer in this conversation in terms of ability to ask questions that are compelling to somebody listening? And then further question is, are we close-- Will we be able to build a system that replaces you as the interviewee in order to create a compelling conversation? How far away are we, do you think?

Um-I think partly I would say, do we want that? I, I really like when we start now with very powerful models, interacting with them and thinking of them more closer to us.

The question is if you remove the human side of the conversation, is that an interesting, you know, is that an interesting artifact? And I would say probably not.

I've seen, for instance, um, last time we spoke, like, was we were talking about StarCraft, um, and creating, you know, agents that play games involves self play.

But ultimately, what people care about was how does this agent behave when the opposite side is, is a human.

I mean, that even today, I would say it's quite plausible that with your creativity, you might actually find very interesting questions that you can filter.

Um, and likewise, if I had now the tools on my side, I could say, "Look, you're asking this interesting question.

From this answer, I like the words chosen by this particular system that created a few words." Completely replacing it feels not exactly exciting to me.

Um, although in my lifetime, I think way-- I mean, given the trajectory, I think it's possible that perhaps there could be interesting, um, maybe self play interviews, as you- you're suggesting, that would look, look or sound qui- quite interesting and probably would educate, or you could learn a topic through listening to one of these interviews at, at a basic level at least.
So you said it doesn't seem exciting to you, but what if exciting is part of the objective function the thing is optimized over? So you c- there's probably a huge amount of data of humans, if you look correctly, of humans communicating online, and there's probably ways to measure the degree of, you know, as it, they talk about engagement.
So you can probably optimize the question that's most created an engaging conversation in the past.
So actually, if you strictly use the word exciting, uh, there is probably a way to create a optimally exciting conversations that are involve AI systems.

I think maybe looping back a bit to, to games and the game industry, when you design algorithms, um, you're thinking about winning as the objective, right, or the reward function.


So it's true that modeling reward beyond the obvious reward functions we've used to in reinforcement learning is definitely very exciting.
[gentle music] You are one of the most brilliant researchers in the history of AI, working across all kinds of modalities.
Uh, so then we're talking about languages, images, even biology, and, uh, games, as we talked about last time.
In your lifetime, will we be able to build an AI system that's able to replace me as the interviewer in this conversation in terms of ability to ask questions that are compelling to somebody listening? And then further question is, are we close-- Will we be able to build a system that replaces you as the interviewee in order to create a compelling conversation? How far away are we, do you think?

Um-I think partly I would say, do we want that? I, I really like when we start now with very powerful models, interacting with them and thinking of them more closer to us.

The question is if you remove the human side of the conversation, is that an interesting, you know, is that an interesting artifact? And I would say probably not.

I've seen, for instance, um, last time we spoke, like, was we were talking about StarCraft, um, and creating, you know, agents that play games involves self play.

But ultimately, what people care about was how does this agent behave when the opposite side is, is a human.

I mean, that even today, I would say it's quite plausible that with your creativity, you might actually find very interesting questions that you can filter.

Um, and likewise, if I had now the tools on my side, I could say, "Look, you're asking this interesting question.

From this answer, I like the words chosen by this particular system that created a few words." Completely replacing it feels not exactly exciting to me.

Um, although in my lifetime, I think way-- I mean, given the trajectory, I think it's possible that perhaps there could be interesting, um, maybe self play interviews, as you- you're suggesting, that would look, look or sound qui- quite interesting and probably would educate, or you could learn a topic through listening to one of these interviews at, at a basic level at least.
So you said it doesn't seem exciting to you, but what if exciting is part of the objective function the thing is optimized over? So you c- there's probably a huge amount of data of humans, if you look correctly, of humans communicating online, and there's probably ways to measure the degree of, you know, as it, they talk about engagement.
So you can probably optimize the question that's most created an engaging conversation in the past.
So actually, if you strictly use the word exciting, uh, there is probably a way to create a optimally exciting conversations that are involve AI systems.

I think maybe looping back a bit to, to games and the game industry, when you design algorithms, um, you're thinking about winning as the objective, right, or the reward function.


So it's true that modeling reward beyond the obvious reward functions we've used to in reinforcement learning is definitely very exciting.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.