Sakana AI Releases âFugu Ultraâ to Match Frontier Performance via Autonomous Model Orchestration.
Our Fugu Ultra model stands shoulder-to-shoulder with leading models like Anthropicâs Fable 5 and Mythos Preview across the industryâs most rigorous engineering, scientific, and reasoning benchmarks while delivering frontier capability without the risk of export controls.
ïŒïŒæ¥æ¬èªã¯è±æã®åŸã«ïŒ We are excited to introduce Sakana Fugu, a new product from Sakana AI that delivers a full multi-agent orchestration system as a single foundation model. Fugu dynamically orchestrates the worldâs best models to tackle complex, multi-step tasks, accessible through a single model API. The result is multi-agent intelligence delivering the very best frontier-level performance without any single-vendor dependency or the complexity of a traditional multi-agent system.
**ð **Sakana Fugu Sakana Fugu is itself a language model trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the worldâs best models to tackle complex, multi-step tasks. Plug collective intelligence directly into your workflows today with a single API.
Beyond Bigger Models: Orchestration Models are the Next Frontier
For the past few years, progress in AI has been driven largely by brute-force scale: building giant, monolithic models trained on ever-larger amounts of data. But hard, real-world tasks require a multitude of specialized knowledge and skills, far beyond any individual benchmark. Unlocking the very best performance therefore requires collective intelligence: knowing which model to use, delegating tasks such as planning and execution, and combining domain-specific strengths while routing around individual weaknesses. Since our founding, Sakana AI has been guided by a core conviction: the most powerful AI systems will not be isolated monoliths, but collaborative ecosystems. Evolution innovates under constraints, and the future belongs to systems that explicitly learn how to coordinate collective intelligence.
Today, this orchestration is no longer just a technical optimization; it has become a geopolitical and operational imperative. Recent disruptions in the AI landscape have demonstrated the severe risk of single-vendor dependency. For an organization or a nation, relying on a single companyâs APIs 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 recently from export controls imposed on Anthropicâs Fable and Mythos models, access can shift or disappear overnight due to changing regulatory boundaries, export controls, and foreign policies.
Collective intelligence serves as the practical hedge against this concentration of power. Sakana Fugu is powered by models trained to be powerful orchestrators with an underlying pool of entirely swappable agents. If a single provider restricts access, Fugu dynamically routes around the disruption. Over time, Sakana Fugu will naturally grow by incorporating newer, more efficient models, including our own. By orchestrating the worldâs models, we are delivering the realistic, resilient blueprint required for AI sovereignty.
What Is Sakana Fugu?
Sakana 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: solving it directly when that is enough, or assembling and coordinating a team of expert models when a task calls for more. It manages model selection, delegation, verification, and synthesis internally, so the complexity of a multi-agent system never reaches your code.
What makes this possible at scale is that Fugu is itself a language model specialized to understand when to delegate, how agents should communicate, and how to combine their work into a single, reliable answer. This approach builds on our research on learned model orchestration, including our recent ICLR 2026 papers Trinity and the Conductor. From the outside, you simply call one model. On the inside, a coordinated system of experts is doing the work.
Fugu and Fugu Ultra
At launch, Sakana Fugu comes in two models, so you can match the system to your workload. Both models can be accessed via a single OpenAI-compatible API.
Fugu balances strong performance with low latency, making it a great default for everyday work. It fits naturally into tools like Codex for coding and code review, as well as chatbots and other interactive services. For teams with data, privacy, or compliance requirements, Fugu also lets you opt specific agents out of its pool.
Fugu Ultra is tuned for maximum answer quality on hard, multi-step problems, coordinating a deeper pool of expert agents when accuracy and depth matter most. Early users have relied on it for demanding work such as AI research, paper reproduction, cybersecurity analysis, and literature and patent investigations.
Here is how the two models perform across standard benchmarks:
Our Fugu Ultra model stands shoulder-to-shoulder with leading models like Fable 5 and Mythos Preview across the industryâs most rigorous engineering, scientific, and reasoning benchmarks. It delivers frontier capability without the risk of export controls.
*Performance comparison of Fugu models and baseline frontier models across a suite of coding, reasoning, scientific, and agentic benchmarks. All scores other than Fuguâs are reported by the model providers. For Fable 5 and Mythos Preview, we report the max of the two if both scores are available on the same benchmark. Neither of them is in Fuguâs agent pool as they are not publicly accessible. For more details, please refer to our *technical report.
Benchmark results comparing Fugu with underlying foundation models used by Fugu, where highest scores are in boldface and the second highest are underlined:
ïŒWe use the mini-swe-agent as the scaffolding for this task.
â We use model provider-reported scores for the baselines.
What Early Users Are Building
Benchmarks tell only part of the story. Fuguâs value shows up most clearly in long, messy, real-world workflows, which is exactly what we focused on during our beta program with close to 500 early users, whose feedback helped us improve the system.
Applications of Fugu Models. In our experiments, we find that Fugu Models consistently outperform frontier models Gemini 3.1 Pro (high), Opus 4.8 (max), and GPT 5.5 (xhigh) for various applications, such as AutoResearch, Rubikâs Cube, Mechanical Design, Japanese Handwriting Analysis, One-Shot Chess, Financial Time Series Prediction.
One of the clearest signals came from automated data science research: early users running Sakana Fugu in an almost fully automated research mode saw it drive meaningful progress with little to no human intervention. For us, this is exactly the kind of task Fugu Ultra is designed for: open-ended, multi-step work where the system needs to explore ideas, run experiments, interpret failures, revise its approach, and keep making progress over time.
Here is what other users are saying:
âFor code review, Fugu Ultra is significantly better than GPT-5.5. It gives comprehensive answers and finds the bugs others miss. Where other tools flag about three issues, Fugu surfaced more than twenty. It's become the model I run all my reviews through.â *
** â Software Engineer, on Coding and Code Review **
âRaw output quality is on par with top frontier models, but Fugu showed unusually strong persona stability across long sessions, holding its identity where other models drift. For agent products, that may matter more than raw benchmark scores. *
** â Executive at Enterprise Platform Company, on Orchestration Quality **
âGiven one scoped instruction, Fugu drove a full security assessment end-to-end â recon, XSS/SQLi checks, auth review, and a clean report with evidence and retest steps â staying inside scope and avoiding destructive actions.â *
** â Cyber Security Engineer, on Security Assessment Analysis **
We saw similar patterns across paper reproduction, cybersecurity analysis, code review, and literature and patent investigations. In these workflows, the value of Fugu is not just a better answer to one prompt, but sustained progress across many steps: reading, implementing, testing, comparing evidence, finding gaps, and producing a useful final analysis or report. The beta made clear that multi-agent orchestration matters most when the task is messy, long-running, and difficult to solve with a single model call.
Sakana Fugu is generally available today. You can access both Fugu and Fugu Ultra through a single API, with subscription tiers for everyday use and a pay-as-you-go plan for heavier and enterprise workloads. To get started, visit our product page or console site.
Looking Ahead
We are deeply grateful to our early users who put Fugu through real, demanding work and helped us shape what it is today. This launch is a starting point, not a finish line. Because Fugu is built on learned orchestration rather than fixed workflows, it improves as the underlying ecosystem improves: as new frontier models arrive, we can fold them into Fuguâs agent pool and pass the gains on to you. In the months ahead, we plan to expand the pool of expert agents, including open models and Sakana AIâs own models, to strengthen coordination for long-running and agentic tasks, and give users more control over how Fugu works on their behalf. We are excited to see what you build with it.
We are looking for people to help shape the future of AI together with Sakana AI. Please see our careers page.
Publications
Sakana Fugu Technical Report, Fugu Team, Sakana AI, 2026.
Xu, Sun, Schwendeman, Nielsen, Cetin, Tang. TRINITY: An Evolved LLM Coordinator. ICLR 2026.
https://arxiv.org/abs/2512.04695 Nielsen, Cetin, Schwendeman, Sun, Xu, Tang. Learning to Orchestrate Agents in Natural Language with the Conductor. ICLR 2026.
https://arxiv.org/abs/2512.04388 Japanese
Sakana AIãèªåŸçãªã¢ãã«ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã§ããã³ãã£ã¢æ§èœã«äžŠã¶ãFugu UltraããæäŸéå§
Fugu Ultraã¯ããšã³ãžãã¢ãªã³ã°ã»ç§åŠã»æšè«ãšãã£ãæ¥ç屿ã®å³ãããã³ãããŒã¯ã«ãããŠãAnthropicã®Fable 5ãMythos Previewãšãã£ãæå 端ã¢ãã«ã«æ¯è©ããŸããããã茞åºèŠå¶ã®ãªã¹ã¯ãè² ãããšãªããããã³ãã£ã¢ã¬ãã«ã®èœåãçºæ®ããŸãã
Sakana AIã¯ããã«ããšãŒãžã§ã³ãã®ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã·ã¹ãã ãäžã€ã®åºç€ã¢ãã«ãšããŠæäŸããæ°ãããã¯ããSakana FuguïŒãµã«ãã»ãã°ïŒãã®æäŸãéå§ããŸããSakana Fuguã¯ãæé«æ§èœã®ã¢ãã«çŸ€ãåçã«ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ããŠè€éã§å€æ®µéã®ã¿ã¹ã¯ã«åãçµãã·ã¹ãã ã§ãããåäžã®ã¢ãã«APIããå©çšã§ããŸããããã«ãããäžã€ã®ãã³ããŒã«äŸåããããšãªãããŸãèªèº«ã§è€éãªããããã·ã¹ãã ãã€ããããšãªããããã³ãã£ã¢ã¬ãã«ã®æ§èœãåãããã«ããšãŒãžã§ã³ãã®èœåãå©çšã§ããŸãã
**ð **Sakana Fugu Sakana Fuguèªäœãäžã€ã®èšèªã¢ãã«ã§ããããšãŒãžã§ã³ãããŒã«å ã®ããŸããŸãªLLMãåŒã³åºãããã«åŠç¿ãããŠãããããã§ã¯èªåèªèº«ãååž°çã«åŒã³åºãããšããããSakana Fuguã¯ãæé«æ§èœã®ã¢ãã«çŸ€ãåçã«ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ããè€éã§å€æ®µéã®ã¿ã¹ã¯ã«åãçµãããšã§ããã®éåç¥ãäžã€ã®APIã§ããã«ã¯ãŒã¯ãããŒã«çµã¿èŸŒãããšãå¯èœã«ããã
ã¹ã±ãŒãªã³ã°ã®å ãžïŒæ¬¡ã®ããã³ãã£ã¢ãšããŠã®ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã¢ãã«
ãã®æ°å¹ŽãAIã®é²æ©ã¯äž»ã«ã¹ã±ãŒã«ã®è¿œæ±ãããªãã¡å·šå€§ã§äžæå²©ã®ã¢ãã«ããŸããŸã倧éã®ããŒã¿ã§åŠç¿ãããããšã«ãã£ãŠçœåŒãããŠããŸãããããããçŸå®äžçã®é£ããã¿ã¹ã¯ã§ã¯ãåäžã®ã¢ãã«ãäžåºŠåŒã³åºãã ãã§æè¯ã®çµæãåŸãããããšã¯ã»ãšãã©ãããŸãããã©ã®ã¢ãã«ã䜿ããããã€åŠçãå§è²ããããéäžã®äœæ¥ãã©ãæ€èšŒãããããããŠåã ã®ã¢ãã«ã®åŒ±ç¹ãé¿ãã€ã€ãããããã®åŒ·ã¿ãã©ãçµã¿åãããããAIã®æå 端ã®èœåã¯ãããããè€æ°ã¢ãã«ã®éåç¥ãããã«æŽ»çšãããã«é¢ãã倿ã®ç©ã¿éãã«ãã£ãŠåŒãåºãããŸãã
Sakana AIã¯åµæ¥ä»¥æ¥ããã£ãäžã€å€§ããªã¢ãã«ã§ã¯ãªããè€æ°ã®ã¢ãã«ãå調ãããšã³ã·ã¹ãã ãã€ããããšã§æã匷åãªAIã·ã¹ãã ãå®çŸã§ãããšããèãæ¹ã倧åã«ããŠããŸãããçç©é²åãæ§ã ãªå¶çŽã®ããšã§æ°ããªè§£ãèŠã€ããŠããããã«ãéåç¥ãã©ãå調ãããããèªãåŠç¿ããã·ã¹ãã ãããããã¯éèŠã«ãªããšèããŠããŸãã
ãããããªãŒã±ã¹ãã¬ãŒã·ã§ã³ã¯ãæè¡çã«çã«ããªã£ãã¢ãããŒãã§ããã ãã§ã¯ãªããããŸãå°æ¿åŠçã«ããå®åé¢ã§ããé¿ããŠéããªãæè¡ã«ãªã£ãŠããŸããè¿å¹Žã®AIããããååã¯ãåäžãã³ããŒãžã®äŸåãæ±ããæ·±å»ãªãªã¹ã¯ãæµ®ã圫ãã«ããŸãããçµç¹ã«ãšã£ãŠãåœå®¶ã«ãšã£ãŠããéèŠã€ã³ãã©ãéèãè¡æ¿ãäžç€Ÿã®APIã«é Œã£ãŠåããããšã¯ãçŸå®çãªåŒ±ç¹ã«ãªãåŸãŸãããããŠãã®ãªã¹ã¯ã¯ããã¯ãä»®å®ã®è©±ã§ã¯ãªããªã£ãŠããŸããæè¿ã®Anthropicã®Fable 5ããã³Mythos 5ã¢ãã«ã«èª²ããã茞åºèŠå¶ã«èŠãããããã«ãèŠå¶ã®æ çµã¿ã茞åºç®¡çãååœã®æ¿çãå€ããã°ãã¢ã¯ã»ã¹ã®æ¡ä»¶ã¯äžå€ã«ããŠå€ããåŸãŸãã
éåç¥ã«ããã¢ãããŒãã¯ããã®ãããªç¹å®ã®ãã¬ã€ã€ãŒãžã®éäžã«å¯ŸãããçŸå®çãªåãã«ããªããŸããSakana Fuguã¯ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã®ããã®ã¢ãã«ãšããŠåŠç¿ããããã®ã§ããããã®èåŸã§çšããã¢ãã«çŸ€ã¯ãå¿ èŠã«å¿ããŠæè»ã«å ¥ãæ¿ãå¯èœã§ããä»®ã«ãããããã€ããŒãå©çšãå¶éããŠããSakana Fuguã¯ãã®åœ±é¿ãåçã«è¿åããŸããä»åŸã¯ãããæ°ããã¢ãã«ããSakana AIèªèº«ã®ã¢ãã«ããã®ä»ã®ãªãŒãã³ã¢ãã«ããéæããŒã«ã«å ããããå ¥ãæ¿ãããããŠããäºå®ã§ããäžçäžã®ã¢ãã«ããªãŒã±ã¹ãã¬ãŒã·ã§ã³ããããšã§ãAI䞻暩ïŒAI sovereigntyïŒãæ¯ãããçŸå®çã§ç¢ºããªéžæè¢ã瀺ããŠãããããšèããŠããŸãã
Sakana Fuguãšã¯
Sakana Fuguã¯ãåäžã®ã¢ãã«ã®ããã«æ¯ãèããã«ããšãŒãžã§ã³ãã·ã¹ãã ã§ãããŠãŒã¶ãŒãäžã€ã®ãšã³ããã€ã³ãã«ãªã¯ãšã¹ããéããšãSakana Fuguããã®åŠçæ¹æ³ã倿ããŸããåç¬ã¢ãã«ã§ååãªå Žåã¯ãã®ãŸãŸè§£ããããé«åºŠãªå¯Ÿå¿ãæ±ããããå Žåã«ã¯å°éã¢ãã«ã®ããŒã ãç·šæããŠé£æºãããŸããã¢ãã«ã®éžæãå§è²ãæ€èšŒãçµ±åããã¹ãŠå éšã§ç®¡çããããããã«ããšãŒãžã§ã³ãã·ã¹ãã ã®è€éãããŠãŒã¶ãŒã®ã³ãŒãã«åã¶ããšã¯äžåãããŸããã
ãããå¯èœã«ããŠããã®ã¯ãSakana Fuguèªèº«ããå調ã®ä»æ¹ããåŠç¿ããŠããããã§ããã©ã®ã¢ãã«ãäœãæ ããã人æã§å®ããã«ãŒã«ã«åŸãã®ã§ã¯ãªãããã€å§è²ãã¹ããããšãŒãžã§ã³ãå士ãã©ã察話ãã¹ããããããŠããããã®ææãã©ã®ããã«äžã€ã®ä¿¡é Œã§ããçããžãšãŸãšãäžãããããSakana Fuguèªèº«ãåŠç¿ããŸãããã®ã¢ãããŒãã¯ãåŠç¿ã«ããã¢ãã«ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã«é¢ããç§ãã¡ã®æè¿ã®ç ç©¶ã§ããTrinityãConductorïŒããããICLR 2026æ¡æè«æïŒãåºç€ãšããŠããŸããå€ããã¯ããŠãŒã¶ãŒã¯åã«äžã€ã®ã¢ãã«ãåŒã³åºããŠããã ãã§ãããå åŽã§ã¯å調ãããšãã¹ããŒãã®ã·ã¹ãã ãåããŠããŸãã
FuguãšFugu Ultra
ä»åãSakana FuguãšããŠæäŸãéå§ããã®ã¯ãã¯ãŒã¯ããŒãã«åãããŠéžã¹ã2ã€ã®ã¢ãã«ãFuguãšFugu Ultraã§ããããããOpenAIäºæã®åäžã®APIãéããŠå©çšã§ããŸãã
Fuguã¯ãé«ãæ§èœãšäœã¬ã€ãã³ã·ã®ãã©ã³ã¹ã«åªããæ¥åžžçãªæ¥åã®ããã©ã«ããšããŠæé©ãªã¢ãã«ã§ããã³ãŒãã£ã³ã°ãã³ãŒãã¬ãã¥ãŒã«ãããCodexã®ãããªããŒã«ã¯ãã¡ããããã£ããããããã¯ãããšããã€ã³ã¿ã©ã¯ãã£ããªãµãŒãã¹ã«ãèªç¶ã«çµã¿èŸŒããŸããããŒã¿ããã©ã€ãã·ãŒãã³ã³ãã©ã€ã¢ã³ã¹ã«é¢ããèŠä»¶ãæã€ããŒã åãã«ã¯ãç¹å®ã®ãšãŒãžã§ã³ããããŒã«ïŒãšãŒãžã§ã³ã矀ïŒããé€å€ããããšãã§ããŸãã
Fugu Ultraã¯ãå°é£ãªå€æ®µéã®åé¡ã«å¯Ÿããåçå質ãæå€§åãããã調æŽãããŠãããç²ŸåºŠãšæ·±ããæãéèŠãªå Žé¢ã§ã¯ãããåã¿ã®ããå°éãšãŒãžã§ã³ã矀ã飿ºãããŸãããã¹ããŠãŒã¶ãŒã¯ãããŒã¿åæãè«æã®åçŸããµã€ããŒã»ãã¥ãªãã£åæãæç®ã»ç¹èš±èª¿æ»ãšãã£ãè² è·ã®é«ãæ¥åã§Fugu UltraãæŽ»çšããŠããŸããã
FuguãšFugu Ultraã®æšæºçãªãã³ãããŒã¯ã«ãããæ§èœã¯ä»¥äžã®éãã§ãã
ã³ãŒãã£ã³ã°ããªãŒãºãã³ã°ãç§åŠããšãŒãžã§ã³ãèœåã«é¢ãããã³ãããŒã¯çŸ€ã«ããããFuguã¢ãã«ãšããŒã¹ã©ã€ã³ã®ããã³ãã£ã¢ã¢ãã«ã®æ§èœæ¯èŒãFugu以å€ã®ã¹ã³ã¢ã¯ãããããåã¢ãã«æäŸå ãå ¬è¡šããå€ãFable 5ãšMythos Previewã«ã€ããŠã¯ãåäžãã³ãããŒã¯ã§äž¡æ¹ã®ã¹ã³ã¢ãå ¥æã§ããå Žåããã®é«ãæ¹ãæ¡çšããïŒäž¡ã¢ãã«ã¯äžè¬æäŸãããŠããªããããFuguã®ãšãŒãžã§ã³ãããŒã«ã«ã¯å«ãŸããŠããªãïŒã詳现ã¯ãã¯ãã«ã«ã¬ããŒããåç §ã
Sakana FuguãšãSakana Fuguãå éšã§å©çšããåºç€ã¢ãã«ãæ¯èŒãããã³ãããŒã¯çµæã¯ä»¥äžã®éãã§ãã
ïŒãã®ã¿ã¹ã¯ã®ã¹ãã£ãã©ãŒã«ãã£ã³ã°ã«ã¯mini-swe-agentã䜿çšã
â ããŒã¹ã©ã€ã³ã®ã¹ã³ã¢ã¯åã¢ãã«æäŸå ã«ããå ¬è¡šå€ã
ãã¹ããŠãŒã¶ãŒãèŠåºããSakana Fuguã®å
Sakana Fuguã®ç䟡ã¯ããã³ãããŒã¯ã®ç¹æ°ã ãã§ã¯æž¬ããããŸãããé·ãå ¥ãçµãã çŸå®äžçã®ã¯ãŒã¯ãããŒã«ãããŠããããã®äŸ¡å€ãçŸããããã§ãããã®ããšã確ãããããã500åè¿ããã¹ã¿ãŒã®ååãåŸãŠããŒã¿ããã°ã©ã ã宿œããããã§å¯ãããããã£ãŒãããã¯ãããšã«ã·ã¹ãã ãæ¹åããŸããã
Fuguã¢ãã«ã®æŽ»çšäŸã AutoResearchãã«ãŒããã¯ãã¥ãŒããæ©æ¢°èšèšãæ¥æ¬èªã®ææžãæåè§£æããã§ã¹ãéèæç³»åäºæž¬ãšãã£ãå®éšãè¡ã£ãããããã®çšéã«ãããŠããFuguã¢ãã«ã¯ããã³ãã£ã¢ã¢ãã«ã§ããGemini 3.1 ProïŒhighïŒãOpus 4.8ïŒmaxïŒãGPT 5.5ïŒxhighïŒãäžåãããšã瀺ãããã
ããŒã¿ãã¹ãã§ã¯ããããŠãŒã¶ãŒã¯ãSakana Fuguã®ãªãµãŒãã¢ãŒããçšããŠãããŒã¿åæãã»ãŒèªåã§é²ããŸãããããŒã¿åæã¯ããŸãã«Fugu Ultraãæ³å®ããŠããã¿ã¹ã¯ãã®ãã®ã§ããã¢ã€ãã¢ãæ¢çŽ¢ããå®éšãå®è¡ãã倱æãèªã¿è§£ããã¢ãããŒããä¿®æ£ããªãããé·ãæéããããŠå°ããã€åé²ãç¶ãããçãã®å®ãŸããªã倿®µéã®äœæ¥ã ããã§ãã
ãã®ä»ãå®éã«å¯ãããã声ã玹ä»ããŸãã
ãã³ãŒãã¬ãã¥ãŒã§ã¯ãFugu Ultra ã¯åçãç¶²çŸ çã§ãä»ã®ã¢ãã«ãèŠéããã°ãŸã§èŠã€ããŠãããŸãããä»ã®ããŒã«ã§ã¯3ä»¶ãããã®åé¡ããææãããªãã£ãã®ã«å¯ŸããSakana Fuguã¯20件以äžãæŽãåºããŠãããŸãããã *
** â ãœãããŠã§ã¢ãšã³ãžã㢠**
ãçŽ ã®åºåå質ã¯ãããã¯ã©ã¹ã®ããã³ãã£ã¢ã¢ãã«ãšåçã ãšæããŸãããå ã㊠Sakana Fuguã¯ãé·æéã®ã»ãã·ã§ã³ã§ããã«ãœããå®å®ããŠãããä»ã®ã¢ãã«ãªã厩ããŠããŸãå Žé¢ã§ããã£ã©ã¯ã¿ãŒãä¿ã¡ç¶ããŸããããšãŒãžã§ã³ãã«ãšã£ãŠã¯ãããã¯åçŽãªãã³ãããŒã¯ã¹ã³ã¢ä»¥äžã«éèŠãªããšã§ããã *
** â ãšã³ã¿ãŒãã©ã€ãºåããã©ãããã©ãŒã äŒæ¥ã®çµå¶å±€ **
ãç¯å²ãçµã£ãæç€ºãäžã€æž¡ããã ãã§ãSakana Fuguã¯æ å ±åéãã XSS/SQLi ã®æ€æ»ãèªèšŒãŸããã®ã¬ãã¥ãŒãããã«èšŒæ ãšåãã¹ãæé ãåããæŽç¶ãšããã¬ããŒãäœæãŸã§ãã»ãã¥ãªãã£è©äŸ¡ãäžæ°é貫ã§ããªããŸããããããæå®ããç¯å²ãéžè±ãããã·ã¹ãã ãå£ããããªæäœãé¿ããŠãããŸãããã *
** â ãµã€ããŒã»ãã¥ãªãã£ãšã³ãžã㢠**
è«æã®åçŸããµã€ããŒã»ãã¥ãªãã£åæãã³ãŒãã¬ãã¥ãŒãæç®ã»ç¹èš±èª¿æ»ãªã©ããããã®ã¯ãŒã¯ãããŒã§Sakana Fuguããããã䟡å€ã¯ãåäžã®ããã³ããã«ããè¯ãåçãè¿ãããšã«ãšã©ãŸããŸãããèªã¿èŸŒã¿ãå®è£ ããã¹ãã蚌æ ã®æ¯èŒãäžè¶³ã®æŽãåºãããããŠæçšãªæçµçãªåæãã¬ããŒãã®äœæãŸã§ãå€ãã®ã¹ãããã«ããã£ãŠçå®ã«åé²ãç¶ããããç¹ã«ãããŸããã¿ã¹ã¯ãå ¥ãçµãã§ããŠé·æéã«åã³ãåäžã®ã¢ãã«åŒã³åºãã§ã¯è§£ãã«ãããããªã¿ã¹ã¯ããããã«ããšãŒãžã§ã³ãã®ãªãŒã±ã¹ãã¬ãŒã·ã§ã³ã¯æã广ãçºæ®ããŸãã
Sakana Fuguã¯ãæ¬æ¥ããäžè¬æäŸãéå§ããŸããFuguãšFugu Ultraã¯ããããåäžã®APIãéããŠå©çšã§ããæ¥åžžå©çšåãã®ãµãã¹ã¯ãªãã·ã§ã³ãã©ã³ã«å ããããè² è·ã®é«ãçšéããšã³ã¿ãŒãã©ã€ãºåãã®åŸé課éãã©ã³ããçšæããŠããŸãã詳ããã¯ãããã¯ãããŒãžãŸãã¯ã³ã³ãœãŒã«ãµã€ããã芧ãã ããã
ãããã«ïŒSakana Fuguã®ãããã
å®éã®è² è·ã®é«ãæ¥åã§Sakana Fuguã詊ãã仿¥ã®å§¿ãžãšç£šãäžããæå©ããããŠãã ãã£ãããŒã¿ãã¹ã¿ãŒã®çããŸã«ãå¿ããæè¬ç³ãäžããŸããä»åã®ãªãªãŒã¹ã¯åºçºç¹ã§ããããŽãŒã«ã§ã¯ãããŸãããSakana Fuguã¯åºå®çãªã¯ãŒã¯ãããŒã§ã¯ãªããåŠç¿ã«ãããªãŒã±ã¹ãã¬ãŒã·ã§ã³ã®äžã«æãç«ã£ãŠããŸãããã®ãããåºç€ãšãªããšã³ã·ã¹ãã ã鲿©ããã»ã©ãSakana Fuguèªèº«ãé²åããŸããæ°ããªããã³ãã£ã¢ã¢ãã«ãç»å Žããã°ããããSakana Fuguã®ãšãŒãžã§ã³ã矀ã«åã蟌ã¿ããã®æ©æµããŠãŒã¶ãŒãžãæž¡ãã§ããŸãã
ä»åŸæ°ã¶æã®ãã¡ã«ãå°éãšãŒãžã§ã³ãã®ããŒã«ãæ¡å ããé·æéã®ã¿ã¹ã¯ããšãŒãžã§ã³ãçãªã¿ã¹ã¯ã«ãããå調ã匷åããSakana Fuguã®æ¯ãèãããŠãŒã¶ãŒããã现ããå¶åŸ¡ã§ããããã«ããŠããäºå®ã§ããçããŸãSakana Fuguã䜿ã£ãŠäœãçã¿åºããŠãã ããã®ããéçºè äžåãå¿ããæ¥œãã¿ã«ããŠããŸãã
Sakana AIã¯ãAIã®æªæ¥ãç§ãã¡ãšäžç·ã«åãæããŠãã ããæ¹ãåéããŠããŸããåœç€Ÿã®åéèŠé ãã芧ãã ããã é¢é£è«æ
Sakana Fugu Technical Report, Fugu Team, Sakana AI, 2026.
Xu, Sun, Schwendeman, Nielsen, Cetin, Tang. TRINITY: An Evolved LLM Coordinator. ICLR 2026.
https://arxiv.org/abs/2512.04695 Nielsen, Cetin, Schwendeman, Sun, Xu, Tang. Learning to Orchestrate Agents in Natural Language with the Conductor. ICLR 2026.
https://arxiv.org/abs/2512.04388