Asimov: Building An Omniscient RL Oracle with ReflectionAI’s Misha Laskin

**Sarah Guo** (0:05)
Hi, listeners, welcome back to No Priors. RL is back with a Vengeance, and one of the most talent-dense new research labs has a product release, a new code comprehension agent. ReflectionAI's co-founders, Misha Laskin and Yana Santanago, work together as leaders at Google DeepMind on groundbreaking projects like AlphaGo, AlphaZero and Gemini. I talked to Misha about building universal superhuman agents, the trickiness of reward modeling, bringing all knowledge work tasks under data distribution, how RL for language and robotics differs, the Windsurf non-acquisition and the landscape from here. Misha, welcome. Thank you for doing this.

**Misha Laskin** (0:42)
Yeah. Thanks, Sarah, for having me.

**Sarah Guo** (0:44)
So it's been about a wild year and a half since you guys started the company. Is that about right?

**Misha Laskin** (0:50)
Roughly a year and a half. Maybe a bit less, but I'd say it's ballpark correct.

**Sarah Guo** (0:53)
Well, can you just start by describing, you said that the company's mission is to build superintelligent autonomous systems, and we've talked before about why this is the moment in time that's possible. What is different about that from building just superintelligence, which is now a more popular, ambitious goal?

**Misha Laskin** (1:11)
At a high level, it's fairly synonymous, but maybe there are different ways of thinking about how to build superintelligence and what that might look like. I think on one spectrum, there's an academic way to look at it, which is, in some sense, to some extent, superintelligence in that sense has already been achieved. So AlphaGo was a superintelligence system, and there were other systems during that time that were built that were superintelligent in narrow domains. And I think you can go for the goal of building a very broad superintelligence by, you know, kind of locking yourself up in an academic, or it's not really an academic, but kind of an industrial lab that is sort of kind of decoupled from product or customers and kind of max out all the benchmarks that are out there and build superintelligence that way. I think that is one approach.
I think the other approach is to kind of think about what is superintelligence more concretely? How is it going to be deployed? What is it actually going to look like in people's hands? And build backwards from there. So I would kind of say that that approach is more kind of co-designing product and research together. Now, the kind of benefits of that approach is that you're kind of you're optimizing for real problems. The constant is that you have to be a lot more focused, right? Because your product kind of defines the sort of capabilities that you want to draw out of the system. And you have to start out a lot more focused before expanding across other product categories and other capabilities. So I would say that on the spectrum of companies that are kind of superintelligence and just a research lab, and then figure out what the product is, you know, once it's built, as opposed to co-designing product and research together to build very powerful systems in what I would call kind of ASI complete categories. You can pick something that is maybe too small of a category to draw out a superintelligence. As long as you pick a category that I would say is kind of big enough to be ASI complete, I think, and this is kind of our approach at Reflection, is it makes a lot more sense to be focused and co-design those two things together, the product of the research.

**Sarah Guo** (3:25)
I want to come back to choice of initial problem in a minute. In terms of just having the intuition and the confidence to say like, we can go do this as a team, we're going to recruit great people and go build reflection, you and your co-founder Yannis were working at Gemini together in Q-Roles before, and previously you had been part of Peter Abil's lab, who's an amazing researcher as well. You described to me as having, I believe the term you used was somewhat muscled your way into AI and deep learning from originally a physics background. How did you decide to go work on this and end up in Peter's lab?

**Misha Laskin** (4:03)
Yeah, as a kid, I became really interested in physics, theoretical physics. It was, I mean, probably a byproduct of I'm Russian, kind of Israeli American and moved around. And then when I landed in the States, it was kind of in a desert in Washington State, learning a new language. And so I had a lot of time in my hands and bumped into my parents had had the Feynman Lectures in their in their library. And so I spent a lot of time just reading what was on the shelf and bumped into that and got really interested in physics.