00:03:34 · Ruby Justice Thelot
[00:03:34] S2: Yeah.
00:03:34 · Qasim Wani
[00:03:34] S0: A lot of them like PostTrainBench, Deep RSI and the Valves RSI Index, they're all like hyper focused on can agents do some groundbreaking research. And while that is like an important and a critical capability for models to be really good at, it's, as FrontierLab, you don't just tell Claude, hey, go build the next version of Claude. It's a lot more sophisticated and a more iterative by design. As researchers, we spend majority of our time looking at the data. And so it's very iterative by design. You're not just, researchers don't really have this idea of I'm going invent the next transformer. They're very like iterative by philosophy. And what we see with a lot of these benchmarks, like let's say PostTrainBench in particular, the benchmark has seven tasks and one of the task is can you take one of the open source quen models and post train it to have the best performance on AIME or GSM8K. The problem with those types of tasks is that's not what you do inside the labs. Like inside the labs you're hill climbing on 20 benchmarks at once and not a single benchmark. And that was sort of like our version of RSI. It's like let's just do what we did at the lab. So I guess a little bit of background about me. I started the RSI efforts at xAI working with Guodong Zhang, who 's one of the founders of the company. And our philosophy when we started working on this was to be able to have Grok invent the next version of Grok, it needs to be good at a multitude of It needs to be really good at model training, but it needs to be equally good at identifying what data to train on. It needs to be really good at creating the environments, doing harness design, eval design, infra. And those are like the primitives required to scale a lab. And so that's where I think a lot of the meta gets lost these days where people like, oh, RSI is just can a model train something, but it's actually much broader than that.
00:05:37 · Ruby Justice Thelot, Qasim Wani, Ruby Justice Thelot
[00:05:37] S1: Totally. Yeah. Yeah. Yeah. Mhmm. So how exactly would you define RSI? Like, what is your definition, personally? [00:05:44] S0: I would say it's really can an agent invent a new lab? [00:05:48] S1: A new lab? [00:05:48] S0: A new lab. A new lab. [00:05:50] S2: Interesting. Like, what can one agent invent a new lab? [00:05:53] S0: Or a swarm of agents. [00:05:54] S2: A swarm of agents. [00:05:55] S1: Yeah. Seems like a really high bar. Like, that seems like a lot higher than what most people describe as RSI. I mean, some people's definition is as simple as like, is the model useful to programmers or AI researchers in any way that would cause the cycle time of new model development to shorten?
00:06:17 · Qasim Wani, Ruby Justice Thelot
[00:06:17] S0: Yeah, I think that I would describe that as self improvement and not recursive self improvement. Like the nomenclature here is on the recursive piece, because the whole premise behind RSI is by virtue of models getting good at very specific capabilities, we should achieve super intelligence. And that's sort of why I really like GDPX as a benchmark because it's not just focused on RSI, it's focused on all the critical components that will yield to super intelligence. RSI just happens to be a direct north star towards measuring for superintelligence. So it is a fairly opinionated answer, but that's what you need. You need people that have an opinionated way of measuring for model progress instead of generic improvement in productivity. It's kind of like saying, what is more important, creating good PowerPoint slides or doing drug discovery? They're both important like, to to... Like, if you're a researcher who can't really talk to a lot of, nontechnical people and you have to do some, like, reporting on material science and drug discovery research, if you don't have good taste in PowerPoints, you're probably not gonna be able to, like, get your agenda out the door. And so our version of RSI is just like, can an agent or a swarm of agents invent the next version of a frontier lab? [00:07:42] S1: Well, why can't they do this already? [00:07:46] S0: They're not good at it. That's sort of how we Yeah. [00:07:49] S1: But like why? Like where where did they come up short?
00:07:49 · Ruby Justice Thelot, Qasim Wani
[00:07:49] S1: But like why? Like where where did they come up short? [00:07:51] S0: So there's so many places. So for GDP x, we observed that the average accuracy or the the mean reward for all the frontier models was not more than 24%, which means that there's still a lot of room to grow for these models to improve on. Part of the reason why these models are not good at it, we sort of talk about it in our blog post within the GDPX report, one of the big problems with models like Astra or Carbon and Opus is that they don't know what experiments to prioritize. Yeah. And as a human, you know, as like engineers and researchers ourselves, like we know that certain experiments are more valuable than other experiments. Now this is not to say that models don't have any sort of intuition on this. They certainly do. It's just that they're not opinionated enough. Opus and sort of the clot models tend to be more opinionated than others, but they still lack that That level sounds right. They still lack that level of like, this is a high taste experiment to run, And by doing this experiment, here's how long roughly I think it should take to finish. And like using that existing logs of information and background research to make the next bet. And that's basically what we were able to find as like, you know, capability gaps in the frontier models.
00:09:18 · S3, Ruby Justice Thelot
Ad[00:09:18] S3: I want to shout out our sponsor, Lovable. You know, the app you've been meaning to build, the internal tool, side project, or product you'd otherwise lose a weekend to? With Lovable, you get software you can ship today. That includes an editable codebase you can inspect and change, plus two way GitHub sync. Lovable also handles the backend and infrastructure, including managed Postgres, auth, storage, hosting, payments, and more, so you don't have to wire it all up yourself. And through Lovable's MCP server, you can create and deploy your project directly from the agents you already use. Turn ideas into software people love with Lovable. Lovable.dev. Now onto the episode. [00:09:56] S2: Wouldn't as a prerequisite for any of that to happen, like, a model would have to have perfect knowledge of all of it, the different, like, of its own weights being hosted within the company and then also of all of the teams, like the pretraining team and the post training team. And, like, do models currently have that level of oversight or sort of, like, omniscience over their current state within the company even before we get to RSI? Is that something that they can do?