After rigorous testing, our joint AI project with Daiwa Securities is entering the full-scale production phase. We're bringing our agentic AI systems to @Daiwa_JP’s wealth management teams to accelerate complex market analysis in volatile markets. Big milestone for Sakana AI!

Our team just shipped Fugu-Ultra v1.1! 🐡 By dynamically orchestrating the latest frontier models, we pushed performance up by 7.9 points. We are now beating Fable 5 in complex coding and reasoning tasks without even having Fable 5 in our agent pool. Collective intelligence is the future.

Sakana Fugu Technical Report Instead of training one larger model, Sakana AI trains an orchestrator that reads each query and dynamically routes or composes GPT-5.5, Gemini-3.1-Pro, Claude Opus 4.8 and other agents into query-specific workflows. With Fugu being the fast router, and Fugu-Ultra being the deep multi-agent conductor, trained with SFT, evolutionary strategies and GRPO to build adaptive scaffolds. The idea is to have the model pick GPT for math, Gemini for science and recall, Opus for debugging, then synthesize them when no single agent is best. This router is able to get SoTA results across SWE-Bench Pro, Terminal Bench, LiveCodeBench, GPQA-Diamond, CharXiv and more, demonstrating the potential of orchestration being a practical alternative beyond training.

Fugu-Ultra is now live on @OpenRouter! ⚡ We share a core vision with the OpenRouter team: the future of AI isn’t a single monolithic model, but the collective intelligence of the world’s best models working together. Try it: 🐡

Excited to partner with @OpenRouter ⚡ Products like OpenRouter Fusion and Sakana Fugu have sparked a serious conversation about dependency and resilience in AI. I believe this is just the start of a great architectural shift to come in AI development.

Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations. I believe the strongest AI systems will become a collective intelligence, too. Since we started Sakana AI, our core conviction has been that the most powerful AI systems will be collaborative ecosystems, not isolated monoliths. Evolution innovates under constraints, and the future belongs to systems that explicitly learn how to coordinate collective intelligence. Today, we are taking a major step toward that future with the launch of Sakana Fugu. Fugu dynamically orchestrates the world’s best models to tackle complex tasks. We are proving that a well-orchestrated pool of swappable agents can match restricted frontier models like Fable and Mythos. But Fugu is about more than just performance. I believe that Orchestration Models are the next frontier, beyond bigger models. Relying on a single company’s model for national infrastructure is a massive risk. As recent export controls have shown, access to top models can disappear overnight. Collective intelligence is the practical hedge against this concentration of power. Fugu simply routes around vendor restrictions by relying on an entirely swappable agent pool. I am incredibly proud of our Tokyo team for shipping this. By orchestrating the world’s models, we are delivering the resilient blueprint required for AI sovereignty. Read our full vision and results here: 🐡

How does it work? Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackle complex, multi-step tasks. As shown in this figure, Fugu is a multi-agent system that behaves like a single model. You send a request to one endpoint, and Fugu decides how to handle it internally. Fugu manages model selection, delegation, verification, and synthesis automatically. It solves tasks directly when that is enough, or coordinates a team of expert models when a problem calls for more. The complexity of a multi-agent system never reaches your code. At launch, Sakana Fugu comes in two models accessed via a single OpenAI-compatible API: • Fugu balances strong performance with low latency for everyday work. It fits naturally into tools like Codex for coding, as well as chatbots and interactive services. You can also opt specific agents out of its pool for data compliance. • Fugu Ultra is our flagship model tuned for maximum answer quality on hard, multi-step problems. It coordinates a deeper pool of expert agents for demanding work like AI research, cybersecurity analysis, and patent investigations.

Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks. Read the full blog: Beyond Bigger Models: Why are Orchestration Models the Next Frontier Progress in AI has been driven largely by giant, monolithic models. But the most powerful systems of the future will be collaborative ecosystems. Today, this orchestration is no longer just a technical optimization. It has become a geopolitical and operational imperative. For an organization or a nation, relying on a single company's model for critical infrastructure, finance, or governance is a material vulnerability. This risk is no longer a hypothetical possibility, but a reality. As we have seen with recent export controls imposed on models like Fable and Mythos, access can disappear overnight. Collective intelligence is the practical hedge against this concentration of power. Because Fugu orchestrates an underlying pool of swappable agents, it simply routes around vendor restrictions. By orchestrating the world’s models, we are delivering the resilient blueprint required for true AI sovereignty.

AI that builds AI - 3 early steps of Recursive Self-Improvement (RSI) ▪️@AnthropicAI: 80% of the code merged into their codebase was authored by Claude ▪️@SakanaAILabs - RSI is their mission. With research like The AI Scientist and Darwin Gödel Machine, they already have one of the strongests foundation for RSI ▪️ @Recursive_SI is automating the research loop itself with the Recursive system, generating and testing improvements to models, training recipes, and GPU kernels. Here is a full guild to what is RSI exactly, how it works in these 3 cases and how they transform research loops today:

In 1991, the foundations for Transformers, Pre-training, Distillation, and World Models were already being built. These helped shape my own thinking, from my time at Google Brain to our Recursive Self-Improvement (RSI) work at @SakanaAILabs today. 🧠🗼 👇

Great collab with @SakanaAILabs on an #ICML26# paper about sparse transformer kernels + formats optimized for modern NVIDIA GPU execution. • TwELL sparse packing • Fused CUDA kernels • 20%+ inference/training speedups at scale Paper + code below 👇

The human brain🧠 is incredibly efficient because it only activates the specific neurons needed for a thought. Modern LLMs naturally try to do this too (> 95% of neurons in feedforward layers stay silent for any given word), but our hardware punishes them for it. One of the most frustrating paradoxes in deep learning: making a model do less math often makes it run slower. Why? Because unstructured sparsity introduces irregular memory access, and GPUs are built for predictable, dense blocks of math. We teamed up with @NVIDIA to try to fix this hardware mismatch. Instead of forcing the GPU to adapt to the sparsity, we built a "Hybrid" format that reshapes the sparsity to fit the GPU. Our sparsity format (TwELL) dynamically routes the 99% of highly sparse tokens through a fast path, and uses a dense backup matrix as a safety valve for the rare, heavy tokens. Through TwELL and a new set of custom CUDA kernels for both LLM inference and training, we translated theoretical sparsity into actual wall-clock speedups: >20% faster training and inference on H100 GPUs, while also cutting energy consumption and memory requirements. Paper: Blog: Code: ⚡️

Today we announced a multi-agent system built with SMBC, one of Japan’s largest banks. It handles complex corporate strategy proposals, reducing a one to two week workflow down to just a few hours.

Incredible work by Sony published in @Nature today! 🏓 They’ve built “Ace”, an autonomous ping-pong robot that uses RL and Sony’s vision sensors to achieve expert-level play in ping pong. A huge leap forward for adaptive robotics.