Sakana AI launches Fugu Max: dynamic multi-agent routing across its largest open-model pool
graceisford · x · 2026-09-11
Sakana AI unveiled Fugu Max and Fugu Ultra v2, the next evolution of its multi-agent orchestration system.
- Core thesis: the frontier that matters is the capability-vs-cost Pareto frontier, yet the industry still treats models as a static menu of isolated options; Fugu Max uses a dynamic architecture that routes each task to the leanest capable model.
- Fugu Max orchestrates the largest pool of open-weights and specialized models to date, including the NVIDIA Nemotron family, claiming performance within striking distance of elite models at much lower cost.
- A live demo and blog post are available; industry figures like Stefania Druga amplified the cost-performance pitch.
More from coding & agent
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- 9-year backend dev: AI code isn't the problem, the rate of making a mess is — Sweaty-Landscape-561 · 2026-09-11
- RTK claims token savings, but our cost benchmarks disagree — michalwarda · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11