
Tokyo-based Sakana AI launched Fugu, a system that coordinates multiple AI models to match Anthropic's Fable 5 and Mythos Preview benchmarks. Fugu is a language model that calls other LLMs from an agent pool, including copies of itself. Two variants ship: base Fugu for low latency and Fugu Ultra for complex multi-step problems.
Tap to vote and see what everyone thinks.
Summary by ByteBrief