The world is changing so quickly. This is probably a little bit obvious, but you should just try things and, like, every day do something with AI. Last summer, I took a weekend and used GPT-5 to help me build an iPhone app. I hadn't done that in a decade. And yeah, it's so fast and so easy. And that was, you know, an age ago. That was like eight months ago. Now it's even faster and easier. Don't limit yourself. Like anything that you imagine, you should just try to use AI and see how far you can get with it, and you'll be, you know, making the world better.
Welcome to another episode of the Light Cone. Ian Fischer is the co-founder and co-CEO of Poetic, which is building recursively self-improving AI reasoning harnesses for LLMs. Previously, he spent a decade as a researcher at Google DeepMind and founded a mobile devtools company through YC years ago. Welcome, Ian.
Thank you. I'm so happy to be here.
What is Poetic? How's it different than RL? You know, how's it different than context engineering?
At Poetic, what we're building is a recursively self-improving system. And so, recursive self-improvement is this, you know, kind of the holy grail of AI where the AI is making itself smarter. The core insight that we had is that we could do recursive self-improvement far faster and cheaper than all of the other ways that people had been proposing to do this. And so obviously I can't go into details about what that is, what our particular approach is, but most of the approaches out there involve, you know, they require you to train a new LLM from scratch, and training LLMs from scratch costs, you know, hundreds of millions of dollars and takes months of effort. And so the...
And then Anthropic or OpenAI will come along and just eat your lunch in the next model release.
Right, right. And, you know, of course, Anthropic and OpenAI and Google, they're exploring training recursive self-improvement, but typically at that level of having to train a new model for every step of self-improvement that they do.
I mean, that seems like actually the defining thing that a startup really, really wants. Like, I know that I want to take advantage of whatever the next model is, but the second you're in fine-tuning land, I'm spending, you know, millions to hundreds of millions of dollars, and then guess what? Like, I just lit it on fire because, you know, the next version of the frontier model comes out and I'll never catch up. Whereas, like, working with your systems means that I will always have the thing that is better than the thing that's out of the box, and that's sort of like the holy grail.
Yeah, we think that this is incredibly valuable to anybody who's building on top of large language models, and we don't view the frontier models as competitors. They're, you know, they're the ones that we're using the stilts, you know, building stilts to stand on top of. But if we didn't have that foundational layer, then, you know, Poetic couldn't exist.
Yeah. I mean, being the smartest model, you know, it's a game of inches actually, and like, so those inches matter a lot.
How do we actually get started? I mean, you've built something that basically any startup could use that it's sort of like stilts really.
We have built a system that can automatically generate systems for your particular problem that will always outperform the underlying language models, and without kind of the massive expense. As you're saying about the bitter lesson, where, you know, what would you have done without Poetic? You probably would have said, okay, we're going to first collect a large data set, you know, like tens of thousands of examples for our particular problem that we're working on, and we're going to fine-tune, you know, the best model we can get our hands on. Maybe that's, you know, one of the frontier models, or maybe it's an open-weights model, doesn't particularly matter. You're going to spend a lot of money on that fine-tuning. The compute is so expensive. And then at the end of it, you have something that, you know, works better than the thing that you fine-tuned on top of, but by then a new model's come out and it's better than the thing that you fine-tuned. You know, you fine-tuned, you know, like three years ago on top of GPT-3.5 or whatever, and then GPT-4o comes out and it just blows you out of the water. And so, are you going to do that again, or are you going to go out of business? And like, in some cases, the latter. With Poetic, what we end up giving you is a, you know, people are calling these things harnesses now, but, you know, or an agentic system or whatever you want to call it, that sits on top of one or more language models and it just performs better than them. And when the new model comes out, that same harness is perfectly compatible with it. And you don't need to change anything to get, you know, an even bigger performance bump. Additionally, we can, you know, continue to optimize for this new model, whatever the new model is that you want to use, and, you know, make it even better. But you don't lose out on, you know, hundreds of millions of dollars. In fact, we do this so much more cheaply than fine-tuning would cost as well.
And you've done this actually a bunch of times, right? Like, I remember when you first came out with your paper in December of last year, you shot to the top of ARC-AGI-2, and then you've done this a bunch of times for other benchmarks too. What, you know, what was that like?
ARC-AGI-2 was this, was kind of us coming out of stealth, letting people know that we could tackle these really hard problems. And in particular, you know, we wanted to show that our system could generate these, what we call, you know, we call our system like the Poetic Meta System, can generate reasoning systems that are highly effective. Gemini 3 Deep Think had just come out. And they were, you know, really quite dramatically at the top of the leaderboard at 45%. And two days later, we released our results where we were showing that we could get a lot higher than that.
So they come out with SOTA, and then you come in right above them every single time, which is like wild to see, honestly. That's what it's like to have stilts, you know, like whatever model comes out, you can be taller than that one with Poetic, which is like, that's so awesome.
Yeah. So the interesting thing is that we were half the cost of Gemini 3 Deep Think because we were building on top of Gemini 3 Pro, which is a much cheaper model, but we still got, in the end, a nine percentage point improvement on the official verification. So they were at 45% and, like, seventy-something dollars, and we were at 54% and $32 per problem.
So recently, you guys just announced some incredible results for Humanity's Last Exam. Can you tell us more about those?
Humanity's Last Exam is a set of 2,500 really, really hard questions written by experts in many different domains. They're meant to be challenging even for PhDs in those fields. AI hasn't passed it yet. But we got to 55%, which is almost two percentage points higher than the previous state-of-the-art, which came out just last week from Anthropic with Claude Opus 4.6. They got 53.1%, and we got 55% on it.
And one thing that Humanity's Last Exam doesn't publish is the cost of getting those results. In your case, this run was done with less than around six figures. How much was it?
We didn't publish any cost for this, but I can say that the optimization cost us less than 100k. Yeah.
Which is impressive because each of these big foundation model train runs are in the hundreds of millions of dollars. And you guys, as a company, you're only seven people.
That's right. Yeah. Yeah. Seven research scientists and research engineers. Yeah.
That's impressive. And I think the thing that's very interesting about your approach is sort of taking a very scientific approach to the emergent behaviors that a lot of the best founders are doing with models. I think a lot of founders that get very good results for agents, they treat the underlying model as a common layer that you can switch in between. And there's certain tasks, for example, for GPT-5.2, like very hard to verify bugs get sent to that, versus architecture that gets sent to Claude 4.6. But you're kind of doing this automatically instead of having a human conducting it, which is very impressive. I think there's something more special going on underneath. Can you tell us a bit about how it works?
