"The world is changing so quickly. This is probably a little bit obvious, but you should just try things and and like every day do something with AI. Last summer, I took a weekend and used um GPT5 to h..."

"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 d..."

">> At Poetic, what we're building is a recursively self-improving system. And so, recursive self-improvement is this uh, you know, kind of the holy grail of AI where the AI is making itself smarter. T..."

">> I mean that seems like actually the like 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-tu..."

">> Yeah. I mean, being the smartest model, uh you know, it's a game of inches actually and like so those inches matter a lot, >> right? Right. >> How do we actually get started? I mean, you've built s..."

"have built a system that um uh 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'..."

"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, uh you shot to the top of ARC AGI V2 and then you'v..."

">> 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 a set of 2500 really really hard questions writt..."

">> Right. You're you're So, you're getting at a core a really core thing. You know, these harnesses, they are um code, prompts, data, you know, built on top of one or more language models, right? And ..."

">> It sounds like this is a complete different paradigm than RL because we went through the scurve of regular pre-training RL with when OpenAI released 01 and now this feels like a new one. It sounds ..."

"with um and then in my spare time I you know do a bunch of context engineering and then the thing is we're sort of like tuning it tuning evals tuning like we're context stuffing ourselves. What does t..."

">> Yeah. And so that definitely varies per problem. But uh what we've seen, in fact, our our last paper at DeepMind was not doing this recursive self-improving stuff, but we were um we were showing th..."

">> So if startups want to use poetic to put their agent on stilts, what should they do? >> Yeah, so right now uh we haven't released anything yet, but uh if you go to poetic.ai, AI. Uh there is a butt..."

">> Slight sort of change change of topic, but something I was curious about. Uh so you arrived at Google over a decade ago when they acquired your first YC startup at portable. A portable was it's por..."

"quickly. This is probably a little bit obvious, but you should just try things and and like every day uh do something uh do something with AI. Always try to push yourself to find the boundaries of wha..."