Sakana AI Releases ‘Fugu Ultra’ to Match Frontier Performance via Autonomous Model Orchestration. Our Fugu Ultra model stands shoulder-to-shoulder with leading models like Anthropic’s Fable 5 and Mythos Preview across the industry’s most rigorous engineering, scientific, and reasoning benchmarks while delivering frontier capability without the risk of export controls.
Survival of the Fittest Code. In the game Core War, assembly-like programs called “warriors” fight for control of a virtual computer. Warriors may employ sophisticated strategies including targeted self-replication, data bombing, and massive multithreading, in order to crash other programs, and dominate the machine. Top: We visualize battles between assembly programs (“warriors”) discovered by our Digital Red Queen (DRQ) algorithm. Each DRQ round introduces one additional warrior into the multi-agent simulation. Bottom: With more rounds, the LLM-driven evolution discovers increasingly robust strategies. By simulating these adversarial dynamics, we observe emergent behaviors that mirror biological evolution, where agents must constantly adapt simply to survive against ever-changing threats. Furthermore, as Core War is a Turing-complete environment where code and data share the same address space, this process leads to some very chaotic self-modifying code dynamics.
Following our 2024 research on evolutionary model merging, a technique for “mixing to create” better models from existing ones (left), we are now tackling the challenge of “mixing to use” frontier models (right). We have developed AB-MCTS, a new inference-time scaling algorithm that enables multiple frontier AI models to cooperate, achieving promising initial results on the ARC-AGI-2 benchmark.
We introduce ALE-Bench, a coding benchmark inspired by hard optimization problems whose true optima are computationally out of reach (e.g., NP-hard). This benchmark enabled the development of our new coding agent, ALE-Agent, designed to tackle hard optimization problems. In May 2025, ALE-Agent achieved 21st out of 1,000 human participants in a live AtCoder Heuristic Competition (AHC), marking a turning point for AI discovery of solutions to hard optimization problems with important real world applications.
At Sakana AI we decided to rethink an important feature at the heart of cognition: time. The Continuous Thought Machine is a new kind of artificial neural network which uses the synchronization between neuron dynamics to solve tasks.
Sakana AI proposed new AI solutions in both the biodefense and disinformation countermeasure categories at a competition jointly hosted by the US Department of Defense’s Defense Innovation Unit (DIU) and the Japanese Ministry of Defense’s Acquisition, Technology & Logistics Agency (ATLA). Out of 60 companies from around the world who participated, Sakana AI won one of the three awards at the competition.
TAID has been accepted as a Spotlight Paper at ICLR, a top international conference in machine learning. With TAID, we have developed TinySwallow-1.5B, a Japanese small language model that achieves state-of-the-art performance among models of similar size.