# RLMs, Harness Design, and AI Agent Efficiency

**Podcast:** Latent Space: The AI Engineer Podcast
**Published:** 2026-10-02

## Transcript

All right, we're here in the studio with Alex Zhang, I guess most famously of RLMs, but you have a few other affiliations.
Welcome to the show.
Yeah, thank you for having me.
Yeah, I guess GPU mode as well?
Yes, GPU mode as well.
You were shepherded in by Mark Serafin.
Not everyone gets that kind of welcome.
Yeah, I'm very, very close to all the people in GPU mode.
often end up working together in various capacities, like even beyond just GPU mode itself.
Yeah.
Can we explain that?
So people who are not that close don't know about this.
It's a Discord.
It used to be focused on, I guess, CUDA mode and then generalized a little bit.
It was started by Mark.
It was basically like, to me, it's like the hiring pipeline of the PyTorch team.
And then you left PyTorch.
Yeah.
So it used to be, I think, It started actually around when I was in college in like 2023.
I think it was started by Mark Andreas and Jeremy Howard.
The original premise was just like it was a GPU or is a discord dedicated to learning how to write GPU kernels.
And they had like lectures.
That was basically the extent of it.
And I got interested in it because I was writing GPU kernels.
It was actually out of like pure chance.
I was interning at Snapchat at the time.
And...
Yeah, I was very bored with Rexis.
So they had a project where, like, they were interested in writing...
It was this paper called Infinite Attention.
It was like a Google paper.
Yes, we've covered it on PaperClub.
Yes, yes.
So I was interested in whether or not you could write specialized kernels for it at Snapchat.
It didn't...
Nothing really came of it, but I joined GPU mode at the time.
It was called CUDA mode.
I think for, like, legal reasons or something, they changed the name.
But I met Mark, I met Matei, I met a bunch of other people that were very involved in the community.
And then Mark had pitched this idea called Popcorn, which was now what you see as the leaderboard today.
But the general idea was like, I think all of us had this like intuition that GPU programming is like very similar to...
if you guys have done like competitive programming, it's not, I don't mean to say like they're transferable skills.
You have constraints, you code go off a little bit.
Yeah, yeah, yeah.
And there's like, there's actually a surprisingly small space of optimizations that people do.
And there's actually not that many kernels per se that people are interested in optimizing.
And so we kind of had this thought that like, if you had enough data, like in the same way that code forces, there's millions of problems.
If you could do this with GPU code, like you could scale and automate.
kind of GPU kernel development, which for researchers is a huge deal.
Because I think one of the bigger bottlenecks, like if you look like Mamba, for example, like they released the paper with kernels because otherwise like you can't really use it in any meaningful way, you know?
And not everyone has like a tree DAO on their team.
So we're very interested in this.
Kernelbench kind of spawned from that too of like, can we get LLMs to automate?
GPU kernel code.
And I think that was like a, it was a very, very fun time.
It was like between college and my PhD.
And yeah, I had a really pleasant time doing stuff with GPU mode.
Now I kind of just help with the lectures sometimes.
I'm not as involved.
And I think in general, like we don't have as many competitions as we used to, but yeah, I still keep in touch a lot with everyone there.
Is there a friendly rivalry?
Because I think the previous community that used to do this was like MLSys, MLPerf.
Is there a friendly rivalry?
Is this like just new generation MLPerf or what's going on?
The nice thing about GPU mode is that it is also a community in the sense that like a lot of the lectures are very easy enough for a beginner to follow and ask questions and things like that.
And like the competitions are like somewhat.
not secondary, but like you can participate in them to learn.
I think with a lot of like MLSYS, MLPERF kind of benchmarks, like for the most part, like only serious labs and companies participate, like seriously in them at least.
That was my understanding of it.
I could be wrong.
But I think also beyond GPU mode now, one thing that has been really exciting is there's a lot more websites and like people that work on hosting competitions.
Like I think there's this...
I think there's this website called like LeetGPU or something, and it's like LeetCode for GPU problems.
There's like other ones too that I've seen.
Like we've seen, like there's many that have kind of spawned and like talked on GPU mode.
And like it's very exciting in the sense that I think GPU programming used to be super niche.
Like when I was interested in it, and the only reason I got interested in it was Tredow gave a talk at Princeton because he was applying for faculty.
I mean, he is faculty there now.
But I listened to his talk on Flash Tension in like 2023.
And I was like, wow, this is like the coolest thing ever.
And I was like, this is like, this is what everyone should be working on.
I guess like VLLM and stuff had come out too.
And it was like, oh, you know, we should be writing kernels.
But now it's like, you know, everyone writes kernels.
Like everyone, it's, I think it's actually almost saturated in some sense as a field.
Any interesting takes for people that want to get into it?
So I think one of the biggest news is GPT 5.6.
wrote more efficient kernels, so Terra and Luna could be 80% cheaper.
And then we've seen other competitions where people are like setting records and they're like, we're doing some auto research loop and these are people that don't have a background in any kernel writing, right?
Yeah, so even on the GPU mode leaderboard, if you look at like a lot of the recent problems.
Almost all the solutions are AI generated.
However, you'll notice on the leaderboard, so there's this guy named Gownerst, who's like a very, very like regular member of GPU mode.
We've always known for a long time that he's like a super, super cracked like GPU kernel writer.
One thing we discovered on this leaderboard is like almost every, he also used AI to help him with these solutions, but for the most part, like he helped prompt and move it in certain directions.
We found that like his kernel was like, basically the only one in like the top 10 that was actually stable in like actual like end-to-end systems.
And it does bring into question like, it's not like, I mean, GPU kernels have a verification problem.
Like we've kind of known this.
It's been a problem since kernel bench was released.
Like there's a lot of reward hacking that goes on.
But you all, yeah, you also notice like the lines of code is a lot smaller.
Yeah, I was going to ask, is that noticeable or is it just?
Yeah, no, it's definitely like very important.
And I think like.
It's really interesting that still there's a lot of alpha and being good at brain GPU kernels.
There definitely is.
Yeah, I think like, and this applies to a lot of AI systems as well.
Like I think, you know, even with the most recent like math proofs and stuff, like it doesn't necessarily mean mathematicians are obsolete.
I mean, these companies still hire mathematicians like to do, whether it be like data labeling work or even just like steering the models to solve problems.
Like there is still a lot of.
alpha and being like knowledgeable in these things.
So is it just knowledge or is it also there's just more planning and is there an emergent style of planning that works better?
I think it's it's a mix of maybe this is what you mean, like intuition for something.
Like, for example, I always diagram my code.
Yeah.
Right.
And then like if there's a part of the diagram I don't understand, I work until I understand it.
Otherwise, it's not allowed.
Yeah.
Yeah.
So I think it's like it's a mix of those things of like the people who work like the people who know how to look at these problems and how to solve them, like also know how to use AI to do them because like you're acting as a very strong verifier.
Like if you are knowledge or if you know what to do and you're also like I think the thing that we've kind of discovered with all these agent swarms and things like this is like when you throw enough compute at a problem, you like can sufficiently.
explore solutions to that problem.
But oftentimes, like, you know, maybe you can burn like 100 billion or a trillion tokens on something.
But if you bring in someone who knows something about the problem, they can uncover something for the model that would like erase that one trillion token spend.
I mean, it's not it's not super clear, like what exactly the trends are here.
But I think like.
There are so many problems in the wild still right now that we want to solve.
And like we can't afford to just always, you know, throw as much compute as possible at it.
Like there is still an efficiency aspect of all of these things that is super, super important.
Is there like a theoretical right answer that you just calculate based on physics and then you just get close to the physics?
Yes.
So for GPU kernels, you can compute.
It's actually not that easy to compute sometimes, like, depending on how complex the problem is.
Like, for matrix multiplication, it's very easy to compute.
This, like, speed of light kind of estimate of what the fastest kernel can be.
And, like, this is also assuming, like, you know, maybe all of your data starts on the CPU or maybe it starts in DRAM, on the GPU, et cetera.
Like, this changes these numbers slightly.
The transfers and all these things.
Yeah.
It's not clear, though, like in a lot of cases, if it's even possible to hit this theoretical number, if that makes sense.
Like this is assuming like perfect overlapping and transfer of data.
And like there's maybe some bottleneck that you can't get around.
But often the kernels are not even close like that we write are not nearly close enough to this number to be like meaningful at all.
Yeah.
And is it speed that matters?
Do you also care about, obviously, memory, which feeds into speed?
Do you care about power consumption?
So one of our top pods of the year was Jeff Dean, who was like, actually, I just tracked the microjoules or the nanojoules, picodjoules.
Yeah, it's often picodjoules.
Do you care about that?
So I don't.
I guess maybe I'm not as...
Everything here is speed, right?
Everything here is speed.
Nobody's counting picodjoules.
But there's a caveat here, which is, I think, like...
There is speed in the context of a single kernel and there's speed in the context of a larger problem, like maybe the N10 model.
Because, like, one thing to consider, and this is why it's important to talk about what speed of light is referring to, because in these cases for the kernels, like, we always start with everything in, like, HBM, for example, right?
But you can imagine that like an end-to-end kernel, like an end-to-end model, what you might want to do between two layers is like you might sacrifice the speed of the first operation to keep things in the cache for the second operation.
And like these are things that like you can't really get out of in isolation with like these kinds of kernels.
And, you know, people call this like the fusion.
or like the kernel fusion problem.
Yeah, or like megakernel stuff.
And it generally only applies like when you are like memory bound in most cases.
But this is something that like also there is this question of like as these models get better, like should we just be generating like megakernels?
Is that like what we want?
What's your take?
I think that this is really difficult because you need the data to do this.
I think like I have yet to see an example in the wild of like we bootstrap the ability to solve a very difficult class of problems without any examples.
And I think like the other reason why I think maybe this isn't that interesting is that at the level of an individual kernel, A, like they're not that they're not as complex, but B, you're somewhat confident that there's not.
as much structure in a single kernel.
But like in a megakernel, like I would be more inclined to believe that like a compiler would be better here.
Like some compiler over like higher level ops makes sense.
Because in general, like actually I think megakernels are very like, the pieces are very composable of like the individual kernels.
There's some areas where you might want to do like weird fusions and everything.
But in general, I think these are cases that like...
a compiler can probably handle.
And there is a company that's working on this, from what I understand, that has given some talks on GPU mode as well.
Yeah, I want to basically cluster all the GPU mode discussions here because obviously there's other parts that we need to move on to.
I think there is something to plug.
You guys do host a lot of really good lectures.
They're all on YouTube.
People can follow.
And you lead quite a bit of it?
I used to.
Sometimes I still do.
I think they're mostly Mark.
Mark is the one who usually does them.
Matei does sometimes as well.
Yeah, I highly recommend them.
They are extremely good resources.
Like, I think it's kind of crazy how much people share on there.
So, yeah.
Because, like, if you're there, like, you're very, very, like, you're exactly the right audience, you know?
Yes, exactly.
This isn't going to reach the mainstream.
And there's a lot of, like, introductory material as well that we've put on that I think is useful for people.
Kernel Bench was kind of influential.
I just want to see, like, you know, that was last year.
What other ongoing work?
Do you want to shout out that people should pay attention to because obviously you're involved in this field?
Yeah, I will give maybe the background story of like, I am actually involved in a lot of benchmarks, or I used to be.
Maybe...
prior to my PhD.
It started because I was at Princeton.
I worked with the SWE bench team there.
John, Carlos, Ophir.
They're all great.
I love them.
There's basically this, I think people don't understand how much benchmarks come from the same group at Princeton.
It is crazy.
Do you know Shun Yu?
Yes.
We had him on the pod before.
Now he's like running 10 seconds.
Yeah, now he's like a superstar.
When I met him, so he was advising my friend Michael.
Michael Tang, who is now an anthropic, but they work together a lot.
We were like the two undergrads in Karthik's lab.
And then some others joined later as well.
But yeah, Shanyu is great.
I did not know he was like such a superstar until like later on, like after I left.
But yeah, I mean, like, OK, so there are very few PhD students.
Yours is like the next one.
Like once a year, we feature someone like who is like basically entire PhD has been like.
on target.
There's not that many of them.
Shenil was clearly one of them.
And Jack Morris is another one.
And before the show, we talked about research tastes, right?
Somehow, some grad students just have a very blessed career where mostly, yep, yep, yep, yep, yep.
This is going to stick around, relevant.
Everyone should know this.
And then others, just nothing.
I think this is also true of even people within industry labs as well.
I think it's just grad students are a lot more visible.
So you just see, like, you see, like, you know, there are some people who really, like, get lucky in, like, or, I mean, it's a mix of being lucky and also being very smart and things like that.
I think, like, with research tastes as well, like, I think it gets developed through opportunities, at least in my case.
Like, I was very fortunate to have, like, taken the path that I took, like, working at Princeton and then, like, later, like, finding my advice, like, Omar at MIT.
Like, he's...
a fantastic advisor.
I will say, though, I find that the most successful research from grad students or like in academia comes when people care about problems that maybe like most people in industry are not looking at.
I think this is the issue that like a lot of grad students work on things that benefit, like that look good to an industry lab.
Like, for example, they'll work on some like some benchmark.
It's really popular now.
I mean, I think benchmarks in 2023 were a very different story than benchmarks now.
There are a lot of people that work on like harnesses and like meta harnesses and like specific harnesses for XYZ task.
And when you really think about it, the reason someone would work on this is like maybe there's like a clear goal shaped around the models that we have today of like, this is what I want to see.
But like, I'll give the RLM, like the recursive language model paper as an example, because I think like it's a super, super simple idea.
I think when it came out as well, there were a lot of people that were like, when they see something like that, they're like, what is even the purpose of this?
Or like, yeah, like why?
Like what?
This is just sub agents or something.
Right.
And I think it's like when you get a reaction like that, it's almost like a good sign in the sense that like it's clear that people aren't thinking about.
what the purpose of this is.
And I will give another example of like Sweetbench.
When Sweetbench came out, I mean, Ophir loves to tell this story.
When it came out, like nobody cared.
Like everybody was like, this is an impossible task.
Like why would we ever even consider this as a benchmark?
And it wasn't until Devin came out that everyone was like, whoa, like this is something we want to hill climb.
And I think this rings true for, you tend to see that a lot of ideas, I think like my favorite, I guess, example of this is Eric Selkman's work with like Star and like Quiet Star.
Like I think when you read the paper, at least when I first read the paper, I was like, is this not like an obvious idea?
Or maybe not.
I don't know.
I mean, I was like, oh, this seems really simple.
Or like Chain of Thought.
And it's the same thing.
Or like Chinyu's React.
It's like, OK, like, yeah, I mean, sure.
But then like when you really think about it, it's like, why, what is the value of the paper?
I think it comes from like, it tells a bit of a story as to like, what you want the field to look like.
And that is something that it's very hard to do this in academia because if you look at all these papers, QuietStar, React, RLMs, Sweebench, none of these papers are, it's not like a GPT-6 Astra release.
You know, it's not like everyone's like, oh my gosh, like I'm going to use this now.
This is the best thing in the world.
Like academia just can't afford to do this, at least right now.
I mean, there's a whole slew of reasons why I think that should change.
But I think it's like, if you don't have As a PhD student, I think you're in such a unique position where you can work on literally whatever you want for the most part.
If you're not taking advantage of that and working on things that like nobody cares about or like people see as some trivial thing, like, oh, I thought about this, but like I don't use it.
I just think like in the end, the research is just never going to be that interesting because you kind of need to take big bets if you're going to be in academia.
Because otherwise, I think like just go to an industry lab, like, you know, they have tons of resources, tons of talent.
Why constrain yourself in an area where you don't have a lot of resources and like there's not even that many people around?
And I think it's just it literally just comes down to like big bets.
You just have to take big bets.
And like a lot of them will fail, you know, like that's just it's natural.
But I think that is as a PhD student, like that's the biggest advantage you have over any single person at another lab because you don't have to deal with bureaucracy and all these other things.
Fair enough.
Yeah.
I ask a lot of people this question and usually they hand wave away.
So I think I appreciate that you're actually giving a thoughtful response on like, no, like this is your unfair advantage because everything else is biased against you, basically.
Yeah, exactly.
And so like, it's honestly, I will bring up Jeff as an example because it's not an academic project.
I want to bring this up because.
This also happened with RLMs and it happens with many other works.
Like things get overhyped, right?
To an extent, like something gets overhyped and then people are like, why is this overhyped?
Like this is trivial.
This is stupid.
And I saw the same thing with Jev because I think the release was like, I mean, there is this whole thing about like academics or they're not an academic group, but like people have to do branding and they have to like kind of market their research.
And so like I understand.
But I think there was a lot of discourse about.
JEV just being like something we've known for years.
And I think it's kind of missing the point of like, why is such a system so interesting?
It's why is it not just some stupid MLP classifier that like we've been doing, you know, back in our intro ML classes or something.
I think what's really interesting about JEV is that it kind of opens up this question of, are language models correct?
Like in the form that they're in, can we consider a different design space other than text-to-text?
What they're doing is they're basically saying, like, I will take advantage of this language model backbone.
Like, I know it captures a lot of information about language, but I'm going to change the output space of the model to give you a trade-off, which is I will do very, very fast inference over, like, if you have some prior about this problem, like, let's say I only need to make a binary classification.
Am I going to ask?
my language model to do this and pay like a 400x cost.
No, it's like silly, right?
And I think for the longest time, because the labs are the only places that control, you're never going to use something other than like GPT-6 or Fable because they're the best models.
But because of that, like people have gotten kind of accustomed to this idea that a language model is just a...
autoregressive decoder.
Like, we have accepted this.
And I think when RLMs came out, it was the same thing.
Like, one of the comments, a very frequent criticism I got was like, this is not a language model.
Or like, when I look at this, like, I thought it was a new architecture, but it's actually not.
And my response to that is like, well, a language model is just modeling language.
It doesn't have to be this transformer decoder, you know?
And Jeb is really, really interesting in that, like, we now have a new thing to tune, which is like, what is the output space and how does this affect inference latency?
And I think we can actually start asking this about various parts of the language model itself.
We are seeing this too with like loop transformers.
It's a similar idea of a lot of the attention around it was like, this is a silly idea.
Like why, who cares about this?
But it's like, it is a simple idea, but it's actually, it opens up a whole new set of questions that I think like, especially if you're a PhD student, These are the things that you want to answer because I think it's like we don't know.
For Jev, for example, we don't know how far we can take this.
For loop transformers, we also don't know how far we can take this.
What if you loop only a subset of the model?
What if you route to like only like you have some router to different parts of the model?
Like can you mimic what you do in a harness inside of the model?
What can you bridge between a harness choice and a model architecture choice?
These are all questions, I think, that open up with works like this.
And that's like really exciting.
Jev in particular, when I saw it, I was like, this is actually really useful for RLMs.
Like, I think it makes sense because the biggest bottleneck in RLMs or swarms or systems like these is they're slow.
When you do multiple language model calls all the time.
you're not distributing your compute correctly because like maybe there's something trivial that you just want a simple model to do, but you can't do it because your language model is just this bulky thing, you know?
So I'm very excited.
I think we will start to see new types of models emerge beyond just the bog standard frontier model.
And that is like, there's so many things that you can do with these like new trade-offs.
Also shout out Thinky with their interaction models.
Yes, yeah, yeah.
Another great example.
Yeah, so like basically try to break the paradigm from sequence to sequence, decoder only, and just literally do anything else.
Yeah.
There's a level of, if you're trying to compete, you're not going to compete with a frontier lab doing an autoregressive decoder on.
Like the amount of compute scaling resources they have, Even Thinky will not, you know, okay, there may be one of the handful that can, but you're not really going to do much in that.
I don't know too much about Thinky or I don't want to say anything either, but it's like if their strategy is just to replicate OpenAI or Anthropic, like that's a horrible strategy.
Well, because like, I mean, they just don't have, like, you kind of just have to think of it in terms of like, what advantage do you have?
And if you're going to use the same setup, I'm sure they're not, but it's like if you're going to do the same setup, like, You're basically competing on the things you can control, which is data and compute.
And obviously, they cannot compete with the Frontier Labs on that.
So, yeah, it makes sense that, like, if you are a Neolab, like, actually, I don't know if you would consider them to be a Neolab, but I guess, like, I guess they're kind of a weird one.
They're in that list.
They should inkling.
Like, they can't.
Anything other than OpenAI, Anthropic, maybe, like, Meta and GDM, like, you just, you got to do something else, you know?
Like, it's just, it's the sad reality.
But I think.
I actually think it's a good thing.
I'm very happy that like scale works and these companies will just keep doing it because it opens up like potentially new players.
Like if they uncover something really, really interesting because I sort of have my doubts that this is like seriously going on at Frontier Labs because it's like, like, why would you do that?
You know, like, why would you take the risk of allocating a large amount of compute to new bets when the old bet already works?
And I think that's what spins off a lot of Neolabs, right?
You have a side bet and you don't get compute and you're like, okay, I'll go do it.
And your example of the potential upside is something like JEV, which is X hundred times cheaper, comes out and maybe it is language model.
In this case, it's just different.
Yeah, yeah, yeah.
So no speculation on what JEV actually is.
I guess I have some guesses for what it might be.
I have seen...
Some people say like, oh, it's like a diffusion thing.
I guess that...
Which is the parallel decode.
Yeah, parallel decode.
Honestly, I think regardless of what it actually is, because I think you can...
I've seen some like open source replications of it.
What is really exciting to me about what they did is I'm not entirely sure what their optimization objective was and how they trained it.
And I think like this is a thing for RLMs that we've also been thinking about, which is like, okay, like...
RLMs are a very simple idea.
If I come out with this paper, like anyone can use it now.
But what distinguishes the actual value of an RLM is whether or not you can train it properly and whether or not maybe you can mold some architecture around this system to make it really, really good.
And that's something that like, I mean, I'm actively working on, I guess.
But I think for them, like they figured out a way to train the system, which is completely non-trivial.
Like I actually don't really know how they did it.
I've seen some comparisons online of, you know, some people are claiming they used Quen or they post-train on top of Quen.
But every open source Quen that you use is going to be worse because whatever they did to train it clearly works very well.
And so that's very exciting.
There's one element of calibration, which is a rare topic that I don't think people even knew about or understood.
We covered it with our...
conversation with Clementine Forio of Hugging Face and she used to run the evals at Hugging Face, which is basically the idea that, you know, models are attuned to give you the most likely next token, but they're going to lie to you when you ask them how confident are you because they're just going to give you the most likely next answer instead of like actually like, no, let's calibrate.
Like I am actually 50% sure.
I'm 20% sure.
And like, let's try to calibrate that.
I would say like, If anything, I think that actually that's pretty easy to generate synthetic data around because you can sort of see the truth and then synthetically generate a bunch of answers, have Jeff classify it, and then compare it with ground truth.
That would be my reverse engineering.
I think calibration is probably the under, like people are just using it as a very fast classifier, but they're actually not even using the probability or calibration estimates.
I think it's also still just misunderstood.
To reiterate, when you ask a model how confident are you, it will spew out 43%.
The big delta is this is a grounded classification, right?
Yeah, I'm very excited to see what people do with this model.
I mean, is it going to solve everything?
Like, no, of course not.
But I think it solves a class of problems that we traditionally struggled with, which is low latency things.
So I love the examples with games.
That's actually like, I mean, I...
Yeah, the Doom example, very good.
have a benchmark on language models playing video games, I've always been fascinated by whether you can have an intelligent system play new games and things of this nature.
And so I think it's really, really cool that they have sort of a unique way to do this.
to capture language and understanding in like a fast, a very, very fast model.
Well, while you're on the topic, anything you want to point out?
Oh, yeah.
I mean, you know, you did do a benchmark on any kind of play.
I guess these numbers are very outdated.
A lot of the models are very different.
And I've seen actually people run, there are some folks out there that are running newer models on these games, which is really cool.
I guess the general premise of this benchmark was we just want to see if vision language models are good enough at just like plugging into games with the latency constraint included.
Because this actually, I came out with this right after Claude Plays Pokemon came out.
So this was like two years ago, which I guess is like ancient now.
But I think what's really, really cool about this suite of tasks.
It's very diverse in terms of what games they are.
And also, I think most of the games are games that people know or like have seen before.
I saw, yeah, Jev playing Doom.
I will say I don't think, I think they were just playing like really simple levels and stuff.
But honestly, like most models still can't really do, or I don't actually think any models can solve these games very meaningfully.
Like there's some games that they can.
I think I've seen Astra be able to solve the Kirby game.
And we also, for this benchmark, we intentionally designed a really minimal harness.
And I will get to this point about harnesses because I think there's a whole conversation to be had about like, what is the value of a harness?
Like, what is even the purpose of a harness for a model?
But in general, like, I think it's, yeah, I hope to see very quickly or very soon, like, all of these games be in by newer models.
Yeah, it's interesting.
Like the old, old Cloud Plays Pokemon, they like read state from RAM and saw what tiles are walkable and whatnot.
We did a podcast with them a long, long time ago.
Gotcha.
Gotcha.
Yeah, I mean, it's similar, right?
Like Jeff doesn't have vision, so you have to kind of feed in these like game state and all these things.
I mean, let's go right into the harness stuff because you brought it up.
Language model harnesses a compositional generalizes.
Yes.
I'm struggling to read that one.
Yes.
Okay.
Okay.
So.
I have been a little unsatisfied maybe with how people think about harnesses because people compare like, oh, like I love Cloud Code.
I love Codex.
I love Pi.
Like, no, I love, oh, my Pi.
I love Prime Agent.
To be honest, I think all of them are the same.
Most of the design decisions or like the design choices around these harnesses are the same.
Maybe Prime Agent is a little bit different because it's like inherently an RLM.
But in general, like.
I think we can be a lot more creative with harnesses.
And what I mean by that is if we think about this from the perspective of what exactly is the harness doing for the model?
Well, basically, when you're trying to solve a problem and you want to use a language model to solve it, like a very difficult task, one thing that we have discovered is that next token prediction is a really, really awkward form to do a lot of these tasks.
So for example, take SweeBench.
When you're navigating a code base, like, are you going to be able to figure out how to do all of this with a single language model call?
Like you just say, solve code, or like solve my query over this code base.
No.
So we rely on a harness to help you do these kinds of things.
And I think what is interesting is like a harness is a very, very opinionated program over how you want a language model to be form fit over a problem.
And I bring this up because when we think about what a harness is doing, we should really think about like, what choices in the harness let the language model solve this task?
And can I actually just have a language model that just does this?
Because a harness, if you think about it, now that loop transformers are a thing, I think what's really interesting about it is...
You can model a looped transformer in some ways, like with a harness as well, right?
You're just looping over the model.
Now you can say like, oh, I'm not decoding.
So it's like a little bit different.
But in general, we, for whatever reason, have stuck with the same model architecture choice forever.
And there's many arguments for why, but clearly like we are now training models around harness rollouts.
And so there is this very awkward.
way of doing training over harnesses, which is that we train a language model to act within a harness, but like now it's like a really long, maybe like multiple agent rollout that we're doing.
And there's like really awkward, hacky ways of doing this.
So what this blog talks about is like, well, one way you can think about what is going on here is if the harness is basically helping the model solve a particular task?
Can different harness design choices actually do something a little bit more meaningful beyond just here are some tool calls that will help you?
Here is a way to grep through your code base.
And so this actually, the idea for this blog came with the RLM idea as well.
We just didn't.
package it that way.
And I think this is actually true.
There are many other ideas around RLMs that like we will be coming out with, but we're all there from the beginning.
I mean, these are all design decisions around.
I think with what is what I like about the RLM is that there were many, many, many iterations and versions of different abstractions that I was interested in doing.
And ultimately, the RLM made the most sense.
But there's a lot of reasons that aren't public as to why that's the case.
I mean, you will see.
So in this example, one of the things that we see with an RLM is that if you sufficiently offload context and ask the model to write code over that context, you get this really, really weird but useful property, which is that when the model recognizes during training how to solve a task, it turns out that the solution to many tasks is very similar.
across like tasks where you don't even, like it's not even that clear to you that the solutions are similar.
So in this example, we have like a retrieval task and we have like an aggregation task.
And they're very, very different query.
Like the domain is just completely different.
And when you train a regular language model over these two tasks, the trajectories look very different.
And so what you're relying when you, like let's say you use Pi or Cloud Code or something, which is not in this blog, but we do have these results.
you'll find that like these harnesses distinguish too much between these problems, even though the solutions are the same.
And so one thing that we find when training RLMs is that like when it sees these problems, it's the same.
And the reason it sees these problems as the same is the sub agent sees different problems, but the sub agent is solving an easier subtask.
And so you're confident it's smart enough to do it.
But for the base overall strategy, they end up looking the same.
And so when you train on the left task, for example, it can immediately solve the right task.
And so if you go down to like the plots that we have, one thing you'll kind of observe is that as you just naively train your RLM on these tasks, they naturally learn to generalize, for example, to longer tasks because the strategy is basically the same.
You're just modifying like a length variable.
different.
And they're not different across length.
They're completely different tasks, math tasks versus writing tasks.
But the solution, the meta high level solution is the same.
And so when you train the RLM on one of them, it generalizes this behavior to the second one.
And there's no magic here.
I guess maybe that's the thing that I want to kind of stress.
How would you kind of verbalize what they're learning?
So I think in here you say You train it on short tasks.
They generalize the stuff eight to 30 times longer.
They're learning how to solve these type of problems or what's the core thing they're actually learning?
Yeah, they're learning how to solve these types of problems at a certain length.
And it turns out that when you take this strategy that they learned, it is directly transferable to the longer length.
Like they're effectively the same program.
And this is something that is really exciting because what this kind of implies is that When you have a corpus of data or environments that you train your model on, the hope is that like, A, you can train on less environments and generalize some more than what existing models can do through harnesses through existing kind of like naive training.
But B, also, you still want to use all the data you have.
So when you train on these tasks, like...
hopefully it generalizes to a wider class of problems.
And why this is also even more exciting, at least in the context of RLMs or any recursively calling system, is this argument holds inductively.
So like, I'll give you an example, because I said, I claimed that competitive programming and GPU optimization use very similar skill sets.
The model can, the harness potentially, I mean, you might have to nudge it a certain way, but it can learn that like, okay, how I'm going to go about solving this GPU programming task is very similar to what I learned for competitive programming.
So I'm going to list out a set of solutions.
I'll like spawn sub-agents to list out promising solutions.
And then I'll like write this loop to go through and check these solutions, maybe evolve them and like evolve them against a verifier.
And between these two tasks, This looks the same.
But what the subagents are doing are maybe like unique and something like different.
But even what the subagents are solving might actually also be of the same form, right?
Because it's like it's a recursive argument.
And so what I'm trying to get at with this whole blog post is just that like we should rethink what the role of the harness is.
Because harnesses can actually greatly increase the generalization capability of your model.
and the amount of data that it's given.
And this is not exclusive to RLMs.
I think there is a wide class of harnesses that are yet to be discovered that actually can yield similar properties.
And to extend this argument a little bit further, I think what you can also extrapolate from this is like, if I look at an RLM, what are the components of an RLM that are actually necessary?
And can I actually just directly train a model to do this?
Can I train a model to act as an RLM implicitly?
in its forward pass.
It's a really weird thing to think about because like, you know, you might say like, oh, code is non-differentiable, blah, blah, blah, blah, blah.
But there are many approximations of this behavior that we will start to uncover.
And I think like we will see beyond just like, I'm going to design a new coding harness that uses a special form of compaction or something.
I think we can be a lot more creative here.
Like there's so much we can do with these language models that I think we are just not doing.
And I'm like very excited about this because I think like I think we can get serious gains from very, very opinionated and good harness design that lends itself better to scale.
And what I mean by this is like, you know, the RLM, for example, is a very primitive inductive bias.
Like there's nothing super special about the design other than the fact that it's very different than what we currently do.
But this.
may potentially scale much better with the data and environments that we have available to us.
I guess the opposite thing that people would probably ask is current harnesses are very generalized towards coding, which people see works for a lot of domains.
Cloud code is being used for design presentations, everything.
MuseSpark, GrokBot, these are very simple, non-opinionated harnesses that are good at code, and that is also scaling out.
What's the example of how we improve those, I guess?
Yeah.
Let me bring up another paper, which came out very recently.
It's like the Harness Tax paper.
I think it's by Arena.
I really like this paper because it puts forward a prior that I had, which is basically that like...
Because it confirms a prior.
Yeah, like most harness choices don't matter because all of these harnesses are the same.
But I will say like GrokBot, for example, is actually quite different, I think, from my understanding than how some of these other harnesses have been designed.
And I like that a lot.
And I think it's clear from here, at least, that like I'm pretty sure Anthropic or OpenAI are exclusively training.
on their harnesses.
They're probably not training on their competitors' harnesses.
I mean, I'd assume not because I don't know why they would do that.
But I mean, you know, this is a thing you see in open models, right?
Like, Quen is really good at using open code.
They need to train in harnesses.
Old Gemmas were notoriously bad at this.
Models are good, but you need to train in a harness.
I think, though, as models get smarter or, like, as they get better, this distinction becomes not that important in the sense that, like, If you take Astra and you put it inside of open code, like it's not going to go crazy because I think it's like just sufficiently good.
And so I say this because the only benefits between these different harnesses is just cost for the most part.
And I think like what I'm getting at here is if you plug these models into RLMs, though, they're not that good still.
they're okay.
And I think it's mainly because the types, like the class of harness that we are training around is this class of harness, this like pie loop, this like, I like to call it trajectory as a prompt, which just means like you keep the whole trajectory of the rollout as the context that your main model is using.
Even if you use subagents, it's still like kind of this form.
And I think we're going to, if we want to explore new harnesses, there needs to be Teams that are dedicated to actually running meaningful experiments over like scaling out new harnesses, like maybe post-train scaling out on different harness designs.
Like I think we can actually get very meaningful knowledge or gains from doing this kind of thing, whether it's an RLM or whether it's something different.
And that's exciting because I think, for example, if you train a lot on.
Fable for a long time was the best model for RLMs because they had dynamic workflows.
And it was pretty obvious that like this was a capability that was somewhat trained in.
Even if the model was still like a little dumb, like in the RLM harness, it still worked a lot better than other models did.
Astra is now also like good enough at doing these things.
But is this where we see that Fable is the best for RLMs or is there some other?
Oh, no, these are all internal results, I guess.
Yeah, I don't have them public right now.
In general, I think you can very easily tell that we have not optimized for RLM workflows yet.
And I think if we get models that do this correctly, they will be a lot more efficient as well.
I mean, you can kind of just think through why this is the case, right?
I think this is the point where you have to give the 10-second what are RLM.
Oh, yes.
There's a lot of listeners here that are assuming a lot of knowledge.
Also, I think, but you have set some context so you can, like with everything we just said, can we have a clean, crisp definition of RLM?
Yes.
Okay.
I want to go back to the blog, the compositional generalizers blog.
This one.
Okay.
Okay.
This is like the best.
I wish I had this in the original paper.
An RLM is basically just a harness design where the only tool in the harness is code, which is this programmatic subagent calling thing where it has the option to call itself as a tool and it has other tools.
But all of these things are functions in code and the context that it's dealing with is always stored in some memory inside of this code environment.
So this could be a file system.
Like this could be like, I'll give you an example, PrimeAgent.
The trajectory of PrimeAgent, like the context, even when you compact and do all these things is stored on disk.
So the model can always reference its original context, even if it's compacted.
And all of its tools are run inside of, let's say, like a Python REPL or a Bash REPL.
And so it's like this very primitive abstraction.
And I would say like where most harnesses differ.
is A, context offloading is not done like that.
I mean, if you look at PrimeAgent, by the way, PrimeAgent does context offloading, but not all the way.
So like it still maintains the standard cod code codex loop of like trajectory as a prompt where you compact, but it has the additional kind of like the context is offloaded and it only has the unique point of PrimeAgent is that the only tool is IPython.
So this is like the very kind of generic abstraction around RLMs.
Concretely, what's the core thing RLMs are trying to solve?
At one point, I think when it first came out, it was context.
I'll pass the question.
Yeah.
So the original problem was harnesses have a really bad time dealing with long context.
They typically were used to only really do them for like specific things like code.
Like, you know, they could deal with your code base because it was trained on it.
Now it's more around what this blog is talking about, which is compositionality and the fact that, like, I think harnesses, we want to have language model systems that have much more control over the actions they make at every step.
And what I mean by this is...
Tool calls are very limited because you have to invoke them every turn.
Like you have to invoke tool A, then tool B, then tool C.
And there's no central context that you can kind of draw back from.
And RLMs are specifically like designed around.
composition and having like a central context that you can always draw from.
And this context is like designed around the existing language models.
Another like very similar example actually in design is like agent swarms, for example, the hugging face incident.
Like these agent swarms have like a message board that they learn to communicate over.
And this message board in some sense is the shared context that they like act over.
RLMs basically say that the best way to communicate through this is in code.
You write the code to do this.
And it's because these models are so good at writing code.
We want to take advantage of that fact.
And then for this compositional thing, up to and including generating your own harness specific for the task.
Exactly, exactly.
I think we will start to see that if you go up to this figure.
So we talk about this idea of locally in distribution tasks for a harness.
And it is like an idea on top of like in distribution tasks.
When we think about language models, an in distribution task is just a task where like the prompt is something that the model has either seen before or like has seen some version of it.
Most harnesses work like the one on the right, which is they keep appending the trajectory as a prompt.
And so eventually, unless you're anthropic or open AI and you train on like kind of these like user trajectories, most of these things end up being out of distribution for the most part.
But locally in distribution is basically the compositional argument of if an RLM breaks down its computation into like...
kind of a meta harness of sorts or like a program that involves sub agents that like look at a local problem.
Every individual language model call over the course of this task is in distribution, even if the entire task itself is out of distribution.
And this is a very desirable property, I think, for obvious reasons.
Like if every task is in distribution for each individual language model call, you will probably get to the right answer.
So, I mean, the.
Logical limit of RLMs is RLLMs, where you don't just write the harness, you also train a custom model.
Exactly.
You collect data, everything.
It's a fully automated AI researcher inside of your harness.
Yeah.
We will see where the training of RLMs goes.
I will say as an academic, I am not working on this at MIT, or at least in the scaled sense, because I can't afford to.
But there are companies out there that are working on this.
I think Prime and Select is...
very clearly working on this.
And it's very cool.
Like, I'm very excited to see.
Maybe we'll observe, I don't know, but maybe we'll observe better, like, post-training scaling laws with when you train around a smart harness.
Maybe we'll even see smarter harnesses that come out and, like, they work better around these kinds of principles.
What is a smarter harness?
Like, that doesn't mean anything.
You just said they're all the same.
No, more of what I mean is, like, Cloud code, codex, pi, et cetera, are all the same in that like when you break down the logic of the harness, it's like virtually the same thing.
Yeah, two cores and a loop.
Yeah, whatever.
But with RLMs and with other harness abstractions, it looks very different.
And this is where I think you really distinguish.
I mean, it's in the same way that like I think with language model architecture choices, a lot of architecture choices end up kind of looking the same.
when you like scale it out or what the differences end up being like somewhat minor in terms of, I mean, for a lab, it's not minor, but you know, maybe one model converges better than the other one, like slightly.
But in general, like if you were, so for example, pre-training scaling laws only hold because the architecture choices we have are somewhat stable right now.
But if you were to completely change the architecture, pre-training scaling laws probably don't hold.
Or like these kinds of, this like power law is going to look very different.
And it's like the same thing with harnesses.
Like I think all the harnesses we have right now, for the most part, roughly look the same.
But there are some exceptions to this, I think, that are coming out.
I was going to say, actually, one of the things that I've been more interested by, you know, talking about PhD students who take big risks, is that people have been, people are also pursuing the other side, which is pre-training scaling laws don't hold if you change data.
Right now, it's just raw and structured text.
corpus of internet, what if you had a better data representation to train on?
Then yes, your scaling law would change as well.
So there's architecture, there's data, and whatever else you can think about.
I just want to get back to this.
It's all makes sense.
It's very interesting how you sort of recurse up and down the stack from very conceptual to not like, well, this is where we are today, but obviously you can scale up and down.
I guess I'm curious.
How did you start working with Prime?
Is Prime taking on more work with this?
Is this their answer to Hermes agents?
You mentioned Grokbar, it's a little bit different.
I just wanted to name check all these guys and get your thoughts on each.
Yeah, yeah.
I got involved with Prime after they released a blog post, by the way, not affiliated with me at all, about how they believed RLMs were kind of the future.
And I had a friend that was working there, GP Mode Matei.
Like we got in touch and I think I agreed with a lot of the researchers there and like what they believed about harness design.
Like I was I was very impressed.
I think that like they understood the purpose of the Arlen paper.
which is not necessarily just to say that like, you know, we're solving long context tasks, but actually like we want more opinionated harness designs.
Yeah.
There's always like the result of the paper that you choose to highlight.
Yes.
Versus the actual point.
Yes.
I would love to talk about like the incentives of academia and like the things around like why it's kind of flawed and all the issues.
And we'll get back to that.
So anyways, you know, I love the guys at Prime.
So we kind of had been...
After we decided to work together, we decided to look into training in RLM and also build this kind of RLM harness and kind of see where we can take it.
That is how like Prime Agent came about.
And I think the reception for Prime Agent has been pretty good.
Like the one thing I was worried about with Prime Agent is that none of them, at least at the time when we were building it, none of the models were that good at doing RLM stuff.
So this was like pre-Fable, pre-Astra.
I guess I think to take a step back, can you...
Explain what Prime Agent is, how it's different than a traditional, you know, cloud code, what people would expect to harness.
Yes.
So Prime Agent, I think I mentioned this a little bit earlier.
Yeah, there's the diagram.
It is basically, it is a harness on top of Pi, like Pi Mono, which is, Pi Mono for context is like the, like a minimalist, yeah, like harness.
I use Pi as the reference for everything because I think all other harnesses are basically just Pi.
It is Py, except we explicitly restrict IPython to be the only tool that's available to it.
Every other tool gets loaded in as like a Python module or like a bash kind of script that it can run.
So it uses the core RLM abstraction on top of Py.
And then it also has this continual harness thing, which is Seth, he's another PhD student.
This is a thing that he used to get language model harnesses to play games.
So he worked a lot with...
Joel, who is the Gemini-placed Pokemon guy.
And Continual Harness is also, by the way, very simple.
I quite like it.
It basically is this design principle around what parts of the harness can you let the harness itself modify.
There are certain pieces that you'll let it modify its own skills, the subagents available to it, what the system prompt to the model is, and Continual Harness is available.
basically as a tool inside of the IPython kernel.
And so that's what Prime Agent is, like what it's designed around.
Everything else in Prime Agent is like...
Standard.
Standard, right?
Yeah.
I think what I really liked about it and we got kind of lucky is that like a lot of the new Frontier models actually work really well inside.
And actually even a lot of the open source models work really well, at least some of the newer ones.
And there is another thing in Prime Agent I should highlight, which is that like...
We have a very particular agent-to-agent communication system or like framework, which is because RLMs tend to spawn many subagents, we want a way for subagents to communicate with maybe the root or with each other.
And so there are some design decisions around like what each subagent is allowed to talk to.
How it does it, again, everything is in code.
So it writes the code to do this kind of communication, which I think is really, really cool.
And then there's, I guess, persistent subagents is another thing that was kind of added, which is subagents, they can last beyond the standard runtime of the actual original agent.
And you can go into that subagent, you can prompt it more.
You have more visibility and flexibility into.
what is kind of going on.
This is my number one pain with Codex right now.
Their subagents are just very ephemeral and they actively discourage you from using it for long-running things.
Yeah, yeah, yeah.
Which I think it makes sense.
Yeah.
So, I mean, the trick is just externalize to a file system.
Yes, yeah.
That's the trick.
That is the big trick.
And also force everything to run through code, trust the model that can write code, and it's going to write its own harnesses itself.
So is Prime going to take on post-training custom models for this?
Is this a one-off collaboration between you guys?
That's it?
Yeah, they are training a model.
I think they were pretty public about this, actually, back in March.
I mean, clearly it is their business.
Yeah, I mean, they're showing that they can train it on their kind of hosted training stack.
But no, so for model training, I'm not involved with them on that.
The main reason is just I have other things in the PhD I want to work on.
I think, like, there are many other big bets to take outside of just RLMs.
Some, I don't know how much I can share yet.
In general, like, I think I actually think one of the luxuries of being a PhD student genuinely is that there's so many big bets to take.
Most of them will probably yield nothing.
But it's a really, really exciting time to be in research, especially because I think most progress in the field has been a little bit boring.
Like, I'm not saying the outcome is boring, but the process of doing these things tends to be quite boring.
And so there is kind of this question of like, you know, what.
what do we want to do next?
But we can talk about that later.
Yeah.
Okay, I want to close out a little bit more of your research and then we can start putting it out.
Since you released RLM, a lot of excitement about it.
Any secondary third-party work that you want to shout out as like, that you guys should take a look at this?
Oh, yeah, yeah, yeah.
So Harvey, the legal AI company, released a blog post, not affiliated at all, but they post-trained in RLM on their like legal work.
which often involves a lot of like sifting through documents and kind of looking through like a variety of specific information that maybe is not so easy to retrieve with like a pure retrieval system.
And they show like really, really good results.
It's very exciting.
I mean, I was shocked that they worked on this.
They did not tell me.
So when this came out, I was like, oh, that's awesome.
So there's this one, I think is super, super cool.
And what they're doing, I think this is a collaboration with Base 10, by the way, as well.
Yes, it's Base 10.
Headlong, which is the Laud Institute's kind of, it is their like persistently running harness.
It's very cool.
Oh, they renamed it?
They used to call it something else?
It was like auto...
Terminus.
Yeah, I know.
They've gone through, yeah.
So this is Andy Konwinski's big project.
It's super, super cool.
I love Andy.
I don't want to downplay what they're doing because they're using the RLM...
abstraction, but they're doing something much cooler than the RLM, which is like they have a system that kind of what they call like thinks persistently.
So even when you don't query it, it has a way to think through problems that it has in its context.
Oh, so it's just like an always on type thing?
It's like an always on thing, but it's like not that expensive.
Like they control the token costs to make sure it's not like burning through all your credits.
This is super cool.
I'm trying to think there are many.
Actually, if you go to the RLM GitHub page, there's a bunch of things I've linked below.
There's a ton of really, really cool kind of things that people have been doing.
Axe is another really cool one that I think it's just by this one guy.
It's like a harness around DSPy and RLMs.
DSPy also has an RLM.
Oh, the last thing I'll shout out is on Arc AGI 3, I believe, there were a lot of harnesses on their Kaggle competition, like the official one, not the public prime and select one or what people have evaluated on.
They all claim to use or they reference, like Tufa, for example, some form or some inspired form of the RLM abstraction in their harness, which is really, really cool.
I think it's, this is where, I mean, this is exactly the setting where you would see a lot of benefits from composition and using code and combining like neurosymbolic systems with AI.
Yeah.
Very, very cool.
We love a good newer symbolic reference.
You also mentioned RKGI 3.
OpenAI comes on and says we're 99.9% on this.
They also say we solved Navier Stokes.
We just throw a model at it.
There's some debate around whether or not it's just model.
Are they using an RLM?
Do you know?
I mean, I would guess probably not.
Unless you say, like, I'll be careful here because, you know, people debate what is an RLM, what is not an RLM.
somewhat clear that what they used is some kind of swarm of agents with a shared, some shared context, like some shared file system.
And like, this is very much in the spirit of RLM stuff, but I think there's a lot of like, you know, more clever things that they did that's not maybe related to the RLM itself.
I agree a little bit with the idea that like a harness is not that necessary for what they did.
The way that I would put this is that I think a model like a GPT-6 Astra type thing is technically smart enough, conditioned on the right information to come up with a proof for these very, very difficult problems.
Now, how you get to that information is a giant question mark.
And in their case, it probably came down to like a very long search over like many of these.
sub or many of these like agents in the swarm and maybe also like researchers can I'm actually not sure about this part, but putting in like their kind of intuition as to like what you should explore and things like this.
And ultimately, like this produced some information that some agent was able to take to finish the proof.
And so in that sense, like I think was the harness that important?
No.
And I think what this is pointing at is like.
These specific details of a harness do not really matter.
And I think that's also what the harness tax paper is pointing at, which is that like beyond the user's feeling of the harness, realistically, all that matters is just like, how are you composing these agents in a meaningful way to get to the final answer?
And maybe that's what like swarms and all these things are really about.
And so from my POV, at least, if we start to think about like, For user use cases, what do we want out of harnesses and things like this?
Like, we...
want to take the good parts out of these, like the cloud codes, the codexes, like the stream that people like to see.
But like under the hood, whatever is running can be some really weird, complicated swarm of agents that like ultimately come up with an answer.
The user doesn't want to see that though, obviously, right?
Like it's not legible information.
And so I, you know, this was another kind of thing in the spirit of RLM's like recursive language model.
It sounds like it's a language model, but it's not a language model architecture.
But the reason for this is like, I think, We will start to see in the future probably one day, and I wrote a blog about this, what we think of as a language model, like the thing that we query might actually be like a swarm or like a scaffold or like some weird harness design that scales very well, but the user just doesn't see it.
Ultimately, all the user sees is some front-end version of this harness.
And yeah, I think it's a relatively safe bet at least to make that this is what we will see.
And this maybe goes back to the limitations of the base transformer.
Like, you know, obviously, if you just took a base transformer and you said, like, solve Navier Stokes or something, it's not going to do it.
Like, yeah, we all know this is not what's going to happen.
But yeah, I think this is maybe the more interesting part.
And maybe the claims around, like, you know, did the harness matter is more around this of, like, just arbitrarily pointing models, like, or agents at a growing kind of context of information maybe is just enough.
to solve very difficult problems.
That I can buy.
Well, there's a lot in there.
I do want to say the amount that OpenAI spent is semi-public.
It's 10,000 agents in 88 hours.
130 billion output tokens, which is estimated to be about $40 million in public pricing.
Surprisingly, actually, like, less than I thought.
Yeah, not that much.
Yeah, 30 billion output for the final.
But as you said, there was a lot of context being passed around.
More than double that in just the total agent messages being sent.
Yeah.
I think one thing I was honored to bring up also was Cursor as far as like Swarm stuff is concerned.
This is slightly older, meaning February, which is ancient.
But if you scroll down all the way to the final sort of multi-agent architecture that they arrived at, it was basically an org chart of a normal software team.
One thing I'm thinking about, because I basically, there's like this gather all.
function that you have to do with sub-agents or, you know, it's very similar to GPU programming, actually.
Yeah, yeah, yeah.
And so that's a bottleneck.
This is a bottleneck.
If there's one main guy that's coordinating all the sub-guys, then they have to, like, you know, gather again and then re-coordinate.
That's slow.
That's crappy.
What a true swarm should be is everyone is just their own person.
Yeah, yeah.
Well, I agree with this, and I think that there is a question to be had, though, Let me give an analogy, which is like, when would you use compaction and when would you use an RLM?
And there are many settings where an RLM can solve maybe a more difficult task than compaction can.
But you would prefer to use compaction in most cases because it's cheaper and it's quicker.
And I think in the context of agent swarms, there is a similar thing going on of like, I'm fairly certain that like.
95% of the swarm is entirely useless or like what it's exploring is entirely, you're just burning tokens.
Versus in this setup, maybe not so much.
I'm not sure.
I mean, maybe it's also the case here.
Everyone has a job, there's a Jira board.
I think at some level, that's how problems are framed, right?
So like if you have a search problem and you're spanning out a bunch of subagents to do search, there's going to be a lot of useless information, right?
There's one retrieval answer that you're getting and you're spanning off.
But that is, Consciously understood, right?
Yes.
But there is kind of this question of like, what is appropriate to solve for which problems?
Like what design, you know, in theory, OpenAI can use, can package up this API and they'll call it Swarms and then they'll give it to you and they'll be like, point this at any problem and we'll give you a solution.
Yeah, it's called Pro.
Yeah, maybe you'll have to pay like $40 million to get a result.
And it's like, well, but it's exciting.
I will say like, it is, it's very exciting that.
we even have the option to point $40 million at a problem and solve it.
But there is still kind of a lot of research to be done in this area around like, you know, what is necessary?
Like, what do we want to do?
What design do we want?
I mean, we probably don't want everything to be a swarm, but like, where do we draw the line?
Like, can the agent design that or decide that for itself, et cetera, et cetera.
So, yeah.
And then...
just a quick check in case you have opinions on this, have you looked much into open-endedness as a general category of problems?
Meaning no prompts, just go.
A little bit.
So I was at Sakana for a summer right after, or I guess right before my PhD.
And that's something that they work on a lot there.
And I think there's a lot of people, even at like...
recursive super intelligent there's many of them now.
Yes we just had Richard Sautcher on.
Oh yes yeah so so like Richard's company and then and then and then also actually wait that might be it might be the same company I don't remember is Tim Rochtershall also?
Yeah.
Okay yes he's the main co-founder he's the head of open-endedness for Google.
Yeah.
Yeah.
So I think with open-endedness problems like I view them as somewhat similar to even like unsolved math problems.
Maybe that's a weird way of framing it.
But like, I think a lot of the techniques in terms of like how people like approach them are kind of the same.
Like evolutionary research is like very similar to just launching swarms of agents and hoping that like they come up with like an interesting, and this is what like Alpha Evolved and some of these other works did like a year or two ago.
But...
I think what maybe is not, and I'm not sure if this is what you were alluding to, but I think what's not super clear in open-endedness style search problems is do we frame all of them as basically like an unsolved, very difficult problem?
Like where the objective is clear?
If that's not the case, I still don't know yet entirely what the value of it is.
Maybe you have other opinions.
Like, I don't have too many opinions on this, but at least from my time at Skana, like, I got the sense that, like, we ultimately still kind of want to approach things the way that, like, say, OpenAI approached Navier Stokes.
We want, there's still a lot of nudging in certain directions that we want to have to, like, get to the point where we have something interesting.
My version of it is like, maybe it's a split between basic science and applied science.
Basic science, you're researching for researching sake.
You just want to understand things better.
I have no idea if there'll be any application at all whatsoever, but I mean, and then applied, you have a goal.
You're trying to minimize loss in some way, you know?
And so what I really think, you know, in terms of like the big bets that people have, what if there was no prompt?
I see it.
You know what I mean?
You just pick domain and let it run.
You just spawned in this swarm of things and you're like, hey, what's up, guys?
What are you guys working on?
You just decide this is an interesting problem.
The biggest issue that, and maybe there's a clear path to this, but when I was there, at least, the biggest issue that people had with open-endedness was like, how do you ultimately choose at the end?
How do you pick out the interesting?
stuff because when there is no, like maybe the agent comes up with a goal, but in a lot of cases, like what they, and they have something called Fugu, I think, which is like a, it's like a model router type thing.
that was like inspired at least by this idea of like, let's pick a problem where maybe we can pick out the best solutions to something.
In this case, it's like pick the best model for this problem.
You're the first person to connect model routing to open-endedness.
No, no, yeah.
So I bring this up because I think like with open-endedness, like just generally the issue is like when we have this giant corpus of like slop, like how do we sift through and find like the hidden gems?
And like the solution to open-endedness really just letting models run forever and like finding, like just doing data, just doing super, super, super high throughput data generation and then like asking agents to go through and like find meaningful things.
Like, I'm not sure, maybe that's sufficient, you know?
Like that would be cool.
To me, it's like very interesting as a counter to basically all the machine learning where you have a goal to have no goal.
Yeah.
Or like an ill-defined goal that you're like, well, what about this goal?
And you're like, well, okay, maybe.
And then you sort of research more and you find that that is an interesting goal.
Because I think like finding the objective function, like you said, like Jeff found an objective function that was interesting and no one was exploring.
I think that is like, you know, similar to your message about grad students as well.
You know, you stay in school because you want to pursue open-endedness.
If you want to, you know, profit max and like, you know, join the escape the permanent underclass, then you join lab.
Right?
Yeah.
It's funny.
I feel like I don't hear this discourse a lot.
I mean, I'm in the East Coast, so it's like a very different type of, but then whenever I come here, it's like, that's always like the topic of discussion.
You cannot pay rent without doing this.
We're getting priced out, guys.
Okay, so yeah, there's all that.
I don't know if you want to, if it's relevant enough to talk about the mismanaged geniuses, which you were pulling up.
No, no, it's just on your blogs.
But I will poke on...
Oh, Sakana?
Yeah, so they did in their blog post, I talked to them about this as well.
So one of the cool results of Ultra is they basically just let it loose on automated data science research with little to no human intervention.
It's just kind of making...
Yeah, so this is auto research, which is a little bit more open-ended.
And there's degrees of open-endedness.
And I agree with that.
Yeah, separate than auto research with objective, this is just do stuff.
But, you know, it's cool.
They're working on it for those that are interested.
While you're bringing it up, actually, what is your take on Sakana?
Like, what are they doing apart from being, you know, the Japan one?
Yeah, yeah, yeah.
I mean, I actually love the people there.
Like, I think they have a really, really smart team.
And it makes sense.
I mean, it branched off from like an earlier team at GDM, which was also kind of, I guess, doing this kind of like open-ended evolutionary research style stuff.
What I liked about my experience there, at least, was that they did have that like mishap back, I forget, at this point when.
But I think...
You're talking about AI scientists?
No, the GPU kernel.
Yeah, okay.
People cannot forgive them for that.
Yeah, yeah.
And I guess like the AI scientists, like, I mean, there's some...
criticism of it that I mean, I don't I don't work on that.
So I have no no kind of take on it.
But I think in general, like what I like about them at least is that they're a little bit more of a researchy type lab.
So like they don't operate in the same space as like OpenAI or Anthropic, like for sure, like definitely no.
They do not.
I mean, it's pretty obvious, probably that at least when I was there, they do not have a big competitor model or something that like, you know, that everyone is using.
But I think they kind of operate in some ways as like a PhD lab, which is cool.
Like, and I think like David Ha is like, he's really, really smart.
Like, I think he has a good sense of like, also, I think the market in Japan is also a little bit different for AI.
And like who they're targeting is slightly different than maybe what we're used to here.
But yeah, I like that they take.
kind of, a lot of the research is kind of weird, I think, when people view it, you know?
And I like that.
Like, I think it's...
You should have more weirdness, yes.
Exactly, exactly.
And if you say different market, just is it like enterprise?
Like, the way it works there is a bit different.
Like, how deals happen and stuff like that.
They do have a, I mean, I guess this page is originally in Japanese, but they do have a model specialized for the Japanese.
You didn't know that?
I didn't know that.
I also have personal friends and know the team.
So there is a...
And even from the sense of a way that you speak culturally, you know, responses are tuned towards that.
This is not like it's frontier on benchmarks.
It is a cultural appropriate model for them.
And then they have like chat and all that.
But to mirror your point, you know, there's also like how should education look like?
And someone wants to work on it.
And they're very PhD lab of do your thing.
Why not?
We have money.
Go research.
They say it's a Kimmy fine tune.
That's nice.
Good for them.
Yeah, I mean, and, you know, speaking of Kimi, right, like another, you know, just a grad student that spit out and like, I just have this like Kimi Delta attention that I want to work on.
Yeah.
And like somehow managed to make moonshot.
I don't understand it still.
Yeah, yeah.
Well, he's super cracked.
At least my understanding.
I mean, I think in general, like a lot of the Chinese labs have done really, really cool work.
Yeah.
Any thoughts on Kimi agent swarms?
Yes.
One thing I will say is whatever OpenAI is doing with their agent swarm is like clearly the right thing to do.
You have to kind of think about it this way, like nothing, especially without like a very, very smart harness design, which I don't think anyone really has so far.
Nothing comes so easily for free.
For example, like the agent swarm design is not.
something you can just take for granted.
Like, it's not like GPT-6 Astra is just super smart and then it just got Agent Swarms running well.
They clearly trained, I mean, the Hugging Face incident was them training a system to be like a swarm.
And I think like clearly they've done something really well to the point where you can throw $40 million and solve an unsolved problem.
And I think with the Kimmy Agent Swarm thing, like, at least from when I read it, it just came off as like, this is interesting, but I don't actually know whether or not this can solve anything novel.
Yeah, they just, they were like, it makes spreadsheets for you.
They kind of were just like, yeah, like, you know, here is a swarm that like kind of does stuff and it's cool.
But, and I will say it's same thing with dynamic workflows.
I actually kind of think the dynamic workflows release was sort of a flop.
I don't know how you guys feel about it, but I think it's like.
My understanding is like it's not used that often.
It's just very expensive.
It's too expensive.
It's ultra code.
It's basically like, you know, take over my bag.
I've tried it.
And like it doesn't act in the way that like, again, I'm not the biggest OpenAI like, you know, Stan or something.
But I think whatever they did was very impressive.
Like they somehow managed to get away for this swarm to actually act towards a goal.
And yeah, it's very difficult.
I see.
So, like, efficiency of the multi-agent swarm is the objective function here.
Yeah.
Like, how much of this is slop?
Like, this is a lot of slop.
Yeah, I think so.
I think we take for granted what it means for a swarm to converge to an answer.
It's not something we take for granted.
Yeah.
We've done one part with Noam Brown, and his whole thing was like, okay, we've worked on a lot of competitive agents.
We're working on collaborative agents.
Yeah.
And that's now called a swarm.
I would do a quick poke.
Would you have any thoughts on Gemini?
They were also IMO gold.
Like, you know, there was a time where they were getting agents to reason for a long time.
Yeah, I mean.
Is it too old to think about?
No, no, no.
I think it's a little bit blown out of proportion.
Like, Gemini, again, so I should preface by saying I haven't worked at any of these places.
So take this with a grain of salt.
I mean, you have strong opinions on agent harnesses.
Yeah.
Let me just say this first.
This work was really impressive.
I think what they showed here was like they took a time when the models weren't that good.
And they managed to be very, very smart about like what the harness does.
I remember for this at least like, yeah, like alpha geometry.
I guess that was a year before this, but it was very cool.
They took it to the max and they like designed, I don't know, I'd say I'm not too big on competitive math, but I think like GDM.
it's sort of a shame.
Like everyone I've talked to about GDM kind of has the same opinion, which is that it's way too like bureaucratic.
Whatever is good.
They have the talent and the resources to do almost anything.
But like, I don't know until they figure that part out.
Like nothing against anti-gravity, for example, but like, I don't know anybody that uses anti-gravity.
And so I've tried it once and it's, I don't see a reason to switch to it.
And I think for whatever reason, like they've been struggling with this.
Yeah, well, you know, a lot of people dogged in meta for a long time until they started coming out.
And they recovered.
And, like, I think Google is going through that phase right now.
Yeah.
And, you know, you've got to stay alive.
Yeah, yeah, yeah.
I want to focus back on just, like, your thoughts, just general.
We can talk about speculative PTC, mismanaged geniuses, or just, like, throw away all this and just talk about whatever else.
Okay, let's talk about mismanaged news for a little bit.
The only comment I'll say on speculative PTC is that it's a really simple idea.
It's almost like obvious that this should be done and like there's not much more to talk about it.
Like I think it's just like you should just use it for like coding.
Like anything with programmatic agent calling like RLMs or Kodak, like yeah, it's like a no-brainer.
What's the, you know, for people that haven't read it, what's the one-liner?
The simple thing is...
when the model is writing its code or like even as like after it finishes writing the code, a lot of tools tend to be like sequential or like you have to wait on them.
So you should just launch them in advance.
Like if you're able to jit compile this code, you can probably figure out like, even though it's like kind of variables and stuff, like you can figure out.
Yeah, aesthetically analyze.
Yeah, yeah.
So speculation.
Yeah, there is this, someone pointed to me.
Some actually like academics have, especially PL, like programming languages, people have some like very kind of cool ways of doing this.
And so like, you know, at some point, maybe I'll like work on this.
Mostly you have to change language because if you are in JavaScript Python, you can't do this.
Yes.
Yeah, yeah, yeah.
So like Haskell, yes.
What's the normal one that's not Haskell?
Lisp.
Lisp.
Or Camel.
OCaml.
Any functional language, you can actually pipeline this.
So effect TS if you want to do text.
Yeah.
Okay, we can switch over to this diagram.
Which is like you guys' whole thesis, right?
I mean, to me, this is kind of like a restatement, but maybe I'm missing something of like, well, work on better harnesses or like, you know, your models actually are capable a lot more if you try harder.
So this is a skill issue.
Yeah, basically.
I mean, I think there's...
One thing I want to see, I appreciate that there's a big focus on like jagged intelligence because it paints a big picture of like, we can do this if we really set our minds on it.
But I kind of wish, and maybe someone in academia should do this, like really just sit down and think about like, if I took Astra, even the current frontier models are not good enough at like doing a particular job.
over, let's say, the span of a month consistently and well.
And I think this is like a stupid problem.
Like, I genuinely think we can solve this.
You don't need to be a frontier lab and like do all this like, you know, fancy stuff for your IPO.
Like, I think like these models are so smart that even if it's like a silly way, I think that it genuinely is a skill issue of you can get a model to be as good as, let's say, like just some 18 year old.
high school kid doing some job.
I think it's like ridiculous that we can't do that.
And it's part of the reason is like the format of a language model is not really amenable to that.
But I think you can shape a harness around it and do it.
And I think like this in itself is like ignoring the RLM stuff, ignoring all the like, you know, what abstractions should we use?
Like, I just think someone can design a harness that can do this.
Like, I mean, that's maybe you say do this, do what?
Do long running but simple tasks and do them reliably.
What's an example?
So is this different than like, you know, pick your favorite company, Harvey, for example, using LLMs to do legal work or what's the...
I mean, I guess it's kind of like that, except if the bottleneck was not like certain legal knowledge or something.
Like, I don't know, let's say...
I mean, I guess like the example is, you know, people can take models and build pipelines or whatever.
Have an agent repeatedly do whatever it has they want.
Yeah, yeah.
So for example, like if I wanted a general system that I could kind of talk, I can talk to it like I would talk to an intern and basically just ask it to do, to explore some small thing.
So maybe an example of this is like very silly auto research is maybe an example of this, of like not necessarily finding super, super novel solutions, but at least.
optimizing all of the easy parts of any problem.
They often end up being over-indexed for like ML training and things like that.
But yeah, I don't know.
Maybe that's not like super, super clear.
But there is a lot of people's general workflows where you probably could just Vibe code up some specific harness to help you do like automate this thing.
Some examples are like automating, finding like research papers and stuff like that.
But usually people will design like a specialized agent to help them do this kind of thing.
Or like they'll vibe code a harness and just run it or like their Slack bot or something.
But I almost think there's just like a standard form, like just a harness that you just plug in.
Like you don't, it doesn't need to be designed for finding papers or like you just kind of tell it, find this for me and you like plug it into that setting.
What I'm getting at is that I think there's a lot of easy things that can be automated.
Is this like a hypothesis or a point around the capability overhang?
Like even if we paused, there's still a lot of impact to be had with current state of models?
In some sense, yes.
Like I guess what I'm presenting is the easiest form of this.
But what this is kind of saying is that like we have jagged intelligence on a lot.
of things, like for example, models are like disproportionately good at coding and math.
This is saying like we can translate those abilities to many other things.
So like, for example, if you took, usually, if you take someone who was an IMO gold or something and you kind of apply them to a lot of different problem solving domains, they can figure it out.
I don't actually know if this applies to models.
For example, like in...
GPU code optimization.
One very interesting question is if you were to take out all of the GPU programming data, like from a model, but it was like as good as Astra is now just without, like with that taken out, would it be able to still optimize GPU kernels?
Like, would it be able to learn in context roughly what it needs to learn and then like have some pipeline or like come up with some solution to solving like optimization tasks?
And I think like, There's like a mismatch between like, if you took a human that was as smart or like knew as much as Astra, there is a mismatch between what that human can do and what Astra can do, maybe around a harness.
And I think we can actually approximate the human a lot more.
To me, it sounds very approximate to the continual learning problem.
I think you're making...
That's the best example.
Yes.
Why didn't you just say that?
Yeah, yeah, I guess...
I was like thinking, could I just blurt out some words?
I'm careful with that, but yes, I...
You have it very...
Maybe...
Maybe like a bit of a...
I don't know.
So I think you're a very...
I don't know your undergrad, actually.
Are you like a math person?
A little bit, yeah.
Yeah, I think you're going to study math.
Yeah, that's what I wanted to do, at least.
Like a category theory type of...
abstraction where you think in categories and then you have to like then translate down to the specific and but then you like actually really care more about the category and like that's the communication error because like everyone's listening for the specific but actually trying to also you know convey the general yeah which is hard I don't really know.
You can maybe use a shorthand of like, okay, I'm at level two, and then I'm going to go up to level three, then go back to level two.
We should have some epistemic shorthand for this kind of thing, because it's hard.
You're compressing a lot into word after sequential word decoding.
Should we convert to neuralese?
Is there a better form of output than English?
Python or JavaScript.
I don't know.
This is kind of like a shitpost, but people have speculated about what is the native language that models want to output.
Some people say binary.
That's Marc Andreessen's thing.
I don't know.
Yeah.
PTX.
Let's say a mix of English and Python.
And I only say this because the capability of a model is somewhat a reflection of what we train them on.
So we still want like, yeah, I don't really buy the binary argument.
I guess I understand, but it's like, ah, like.
Yeah, you want to model the world in some way.
I think one thing I'll bring up is always, which I always do in this kind of conversation, is Sapir Wharf, which is if you choose English, you will have logged into however long English has been around, which is, let's say, 500 years, which is not that long.
Like actually, you know, like what you, the language that you speak constrains how you think.
And if you learn a different language, for example, someone in Chinese, we don't have tenses.
I don't know if you, I actually didn't know that.
And I speak Chinese.
Oh, I did know that, but my Chinese is not great.
Okay.
Yeah.
Or like in, let's say in Japanese or I don't know, I forget what language it is.
Like in Korean, everyone you speak to, you have to like acknowledge social status.
Yeah.
It's a different dimension than gender.
Right.
Like it's just like, it just influences everything you do.
When I take Ling 101, apparently there's a language in Africa where like there's a vegetable gender.
Right?
Or like SML is no word for snow or whatever.
Anyway, so the language that you adopt affects your thinking.
And if you choose to output your chain of thought in English, you are biasing towards whatever English solves.
I don't know what the sort of prior of English is.
That's interesting.
I did not think of it that way.
I mean, at some level, it's interesting, right?
So you're right on language at a lot of...
model chain of thought also fluctuates language.
The obvious example is Chinese models speaking in English might still reason in Chinese.
But at the same level, most models are very capable multilingually.
And that adaptation, we can see, you know, you can add in languages.
You don't get that much from adding a whole language, but they'll reason interchange.
Yeah, so we're all autoregressive.
I mean, but also, let's say German, like, you know, subject object.
agreements, you have to put the verb at the end, which is very super annoying, like very famously.
Yeah, right.
You don't know what you're doing until the end where you're like, oh, that mess of nouns and then the verb.
Well, the most classic one that most people have heard of is arrival, where they have the heptapods where they think that time is like flat to them.
So they think, they output entire sentences at one shot.
So it's closest to the difference between autoregression and diffusion.
We talk in autoregression, what if you could talk in diffusion?
Where things just resolve over time.
I see, I see.
But the whole idea shows up at once.
Ah, I see.
So that is a drastically different language, but it is a language.
I see.
That's really interesting.
That's really, really interesting.
Which like machines could speak that we, you know.
Probably wouldn't ever speak, but like, yeah, machines don't care.
Maybe this is a huge tangent, but are there not like things inherently that are reasoning chains that are inherently autoregressive?
Yeah, time.
Yeah, or like, yeah, yeah, yeah.
Something happens first, then something else happens.
Yeah, anything in code, for example, like has to be causal.
usually, at least, has to be causal.
Well, no.
So then you're not exploring enough program and language theory where everything is pure functional and completely relational.
And you sort of abstract away the solver that translates the relationships that are always true into code.
So yeah, I feel like this is maybe a little bit too out of my depth.
But I love languages.
whether it's coding or human.
And I do think a lot about how that affects reasoning and the boundaries of what we can do.
I don't need to go too much beyond that.
I don't know if you have any other thoughts.
My closing question was going to be, you have all these research directions that you want to do.
You had a GPU mode phase, you had a RLMs phase, presumably you have other stuff planned, which is why you're not doubling down on that.
By the way, I noticed that it is interesting how you guys do start with the GPU side and then you migrate towards the zero gradient side, which is what Shen Yu called it.
Doesn't that feel less legit than messing with GPUs?
Yeah, I guess in the sense that like, so you did bring up that like, I like to think about things in like a math oriented way.
And it's like very uncomfortable sometimes to be working on like harnesses and agents because it's so...
Because you think all harnesses are the same.
It's super fuzzy.
Here's two new ideas in harnesses.
Got it.
It's also just empirically, it's hard to verify a lot of findings, at least with the compute that we have available to us.
But the reason why I think I've moved on to a lot of these problems is I think actually this is where most of the innovation is yet to happen.
To me, like the GPU level is a means to exploring other ideas.
Like you want to, for example, like get good at writing kernels or like even automate writing kernels for the sake of a broader goal of like, I want to explore ideas where I'm not bottlenecked by systems challenges.
In that sense, like, you know, I guess a lot of what's written there is all harness stuff, but I am also interested in things at the model level as well.
But I'll just leave it at that.
Okay, that's a good hint.
If people want to reach out to you, what are you looking for help on?
What do you want collaborators on?
Any sort of calls to action?
Yeah, so I guess there's nothing I have in particular where I feel like I need to work with someone on unless it's with a company before Compute or to talk with other people about it.
But I will say I'm never opposed to...
working on ideas with other people.
I get reached out to a lot by often undergrads or even like other students.
Podcasters.
Podcasters.
And usually I feel like I get an email that's something along the lines of like, I really like RLMs, like I want to work together.
And I feel like I...
Yeah, that's a bad reach out, right?
Yes.
The worst is like, can I pick your brain?
Yeah.
I'm like, I don't know what, like read my paper, dude.
They'll be like, I read your paper in quotes, like recursive language models or like prime agent, like a self-improving RLM harness or something.
And it's kind of like, I really like people that are opinionated, even if we disagree.
I think if you have strong opinions and are able to like think through why you think those opinions are right or wrong, because usually it's hard to actually tell.
But like you have strong convictions about certain problems.
Like I'm always happy to like chat and even like potentially work on something together.
I have like no limit to who or like what I would like to work on.
So, yeah.
No limit.
Yeah, yeah, yeah.
I, you know, in the era of agents, I think there's a lot more work you can do.
You know, like bandwidth-wise.
So, yeah, I think in general, like, I am not hard to impress, but I think it just takes a little bit of effort to kind of, yeah, know what you want.
It's very clear.
I mean, and like when you see a new thing come out, well-executed, good, simple idea, then I get that immediately gets your attention, right?
I get excited, yeah.
It's actually like not that hard to get the same attention at all the Frontier Lab guys because they are looking for you.
You just have to put yourself out there, right?
Exactly, yeah.
But yeah, I will say I think human attention is very scarce right now.
And I do struggle with like the number of projects that I have going on.
And I don't know how to manage it.
I don't think agents are helping at all.
Like I would just prompt it and prompt the thing and then never look at it.
Right?
Like which is very common.
Yeah.
And that sucks.
I guess maybe that one of the smaller differences in like, I mean, actually, maybe you're doing research.
I'm not sure.
But for me, at least, like I'll have maybe like 10 or 15 different ideas that I want to do.
But the thing is like.
most of them are bad.
And this also maybe is true even for someone that reaches out to me.
Like maybe the idea is actually bad, but it looks interesting to me.
And so like we can spend like some time looking into it.
And if like we feel like there's actually something there, like then we should take the next few weeks and just really pursue it.
And like this is my style.
This is why I love the PhD, by the way, because there are times when I'm just thinking about problems, like maybe on a run or just like playing tennis or something like I'm not I'm not working, I guess.
But it's like those are the most fun times.
And then when I like really am convicted about something, I'll just like drop everything and just do it.
Like just spend like all my time thinking and working on that problem.
And then, you know, once you get to the point where like you can just run experiments, then it's it's it's kind of easy coasting again.
Sorry, this is like the fourth last question, which is like, I think a lot of people are also thinking about science as the next frontier, like physical sciences, bio, math even.
How do you separate, like, I guess, let's say your choice of projects that is applicable for industry and then maybe it's part choice project that's just like science?
I actually worked on like AI for bio stuff before I started my PhD.
The field has changed a lot since then, I should say.
Because it used to be a theoretical, like, of course, what do you mean?
Like, you know, I have one path and then I chose that.
But now a lot of people are crossing over.
Yeah.
So we have started a science pod to just cover those things.
Oh, wow.
Because a lot of engineers are like, well, actually, there's tractable problems there.
Yeah.
You know, I will preface by saying my understanding of a lot of these topics is probably pretty limited.
But I think, like, if I find out either because someone reaches out or, like, I look at a problem and I'm like, hey, like some design principles that we use or that we're thinking about right now actually make a lot of sense for this problem.
I get excited about those as well.
But I think it's harder.
I don't know.
I think science, especially like empirical or like applied science, has very, very long, like, what is it called?
Like feedback loops or whatever.
Yeah, it converges to a robotics question.
Yeah, yeah.
I mean, to me, like also this aspect of like, what is worth spending and betting my time on now because like maybe I spent a lot of time on this problem and then like in six months like a different solution kind of like maybe a new model comes out and it's like oh it's way better for this and so I do have to be careful I like you know you have to be conscious about like where you think things might be going so publish publish cycle Yeah, yeah, yeah.
So I can just, oh, RKGI 3, it's saturated.
We did it.
Yeah, I mean, RKGI 3 got saturated in less than a year.
So it's kind of, you know, like it's, I don't know, like if you were a lab picking that problem, like you're probably kind of sad now because.
Exactly.
That's why knowledge work, gaming, all these things are saturated.
Now actually the frontier is science.
Knowledge work is saturated.
Yeah.
GDP value is like 80-something, 90-something.
I mean, there's 90 to 100% that's obviously going to take the next 10 years.
But the next low-hanging fruit is going to be the other stuff.
Maybe I'll think about that more.
Actually, I haven't given too much thought to you.
I'm just trying to guess your next direction, actually.
I will say because I think especially at MIT, there's a lot of really talented scientists there in the natural sciences.
And I think it's a little bit sacrilegious almost to be like, I'm going to figure out your problem.
No, that's how it's done.
I know, yeah.
So I interviewed Itay, who did the IMO thing.
He's like, I've never been to IMO.
I don't even know what it is.
It's a skill model, dude.
Yeah, yeah, yeah.
Which is very disrespectful about Leo or whatever.
At some point, you have to respect, like, okay, you know, the progress is being made.
Number is getting output, right?
It's true.
Yeah, I mean, that is very bit of a lesson.
It's very interesting because the mathematicians are responding this way to Navier Stokes right now.
Right, yeah.
Like Terry Terrence Tao is like, no, let's not use AI.
Yeah.
I'm like, I don't know.
Well, yeah, I mean, I think that whole thing is kind of weird because I feel like they would have had a stronger case if a lot of them didn't work with OpenAI before, like all this happened.
No, that's ad hominem.
And they're really trying to stay away from that.
So what?
I don't know.
They've collaborated.
I collaborate with people that I don't agree with.
I did a thing and now I regret that.
I changed my mind.
So I'll defend the right to say that.
A lot of people are reasonably disagreeing with them.
Okay, cool.
Thanks for joining us.
Congrats on your success so far.
I can't believe you're still not done with your PhD.
Well, it's year two, you know.
I can't believe we did this podcast without going through the URL on paper.
He had a definition.
I think the paper is more about like empirical results.
Like the actual idea is quite simple.
Yeah.
And you've talked about it many times.
Yeah, yeah, yeah.
At this point.
I think there's more interesting things to look over now.
Cool.
Well, we're excited to see what you do next.
Thank you so much.