Sakana AI Introduces TreeQuest Algorithm

we're going to start to see a new tier of AI chat bots. I don't know that you remember uh Sakano or Saka or whatever they're called, but they were one of the first companies to introduce the idea of selfarning AIs, but they've introduced something called Treequest, which is more important than you think and it's become very very relevant. It basically is an open-source technique and it enables multiple artificial intelligence models to work together on complex problems. Now, this is very different from agents. Agents aren't necessarily working together. They're not chucking ideas back and forth. They are just doing these tasks one at a time. Whereas this is multiple agents coming together and asking each other the questions and sort of formalizing their answer together and it's using something called inference time scaling to coordinate multiple frontier models during problem solving. You've got this B a technique called adaptive branch Monte Carlo tree search and a algorithm that allows AI systems to perform trial and error reasoning while deciding which model should handle each step. So they're just like little ants working away. And in testing they they did the ARC uh AGI2 benchmark. A combination of open 4, Gemini 2.5 Pro and DeepC's R1 models solved over 30% of problems compared to 23% for O4 Mini just working alone. So, it's kind of that extra juice. It gives gives these models that extra juice. And what I think is really interesting, you can use different models together. It features a flexible API that allows developers to implement custom scoring generation logic with checkpoint capabilities for longunning tasks. The framework supports both single model and multimodel deployments, making it accessible to organizations with varying tech technical requirements. Really groundbreaking stuff. And I thought that the the whole you know self-arning mechanism was kind of you know the singularity but this is a whole new paradigm alto together that you know they're actually working together and deciding amongst themselves which is the right approach. This is gro heavy. This is super gro heavy and you see it in their graphs. They do the long horizon thing and you see the boost that it gets. So grock on its own is fine and then you've got the time context window or something they call it. then you get that boost and this is exactly what this is. So what that tells me is that Grock are not going to be the first people to implement this. We're going to see this because it's open source. Why wouldn't other models do this by getting that extra thing and then getting that extra buck? Because we know the price of Grock. We're going to start to see a new tier of AI chat bots that offer this agent working together quest functionality. I love that tree quest because they're all branching off and doing their thing. It's cool. Yeah. So, we have this new tool in the in town. I I believe this does the entire thing much different from what you showed. Uh but the results might be very similar. Uh it's called roundtable.now and it's essentially just a bunch of different AIs around the table discussing something together. So, I just signed up literally right now and I asked, is there such a thing as objective morality? So the idea is that each uh GPT each um AI tunes in and they talk about you know what you ask and the idea is that they discuss this um like between each other and then they should come to a conclusion. So here I'm saying like conclude and then we see each essentially chatbot uh trying to come to a conclusion and they see each other's responses. Yeah, this this is uh funny because this is also going to be pretty expensive. I guess I have five models right now, but like if you pay unlimited, you get 20 models at once and then it's a thousand a month or a,000 a year. A month. I think it's going to achieve the same thing, but it's just done in a different way. So the differentiator comes down to whether it's open source or not because you know round table are going to they're going to want to try and earn from subscribers whereas tree quest is sort of open source and that means Gemini and open AI and all the rest of it are going to adopt that and make it their own sort of thing. This is part of a larger conversation on my show Command AI which we stream live every single week. We discuss the news and all things related to AI in the world of design and web. Catch us next week and join in the banter.