Agents

New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trai…

New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model i

DGX agentx-post
agentsdavid-ha--x

New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model is suitable for a given task, but also how to orchestrate queries across diverse multi-turn model query sequences. Thereby, it can provide more than just an argmax over a model pool 🐟 Throughout the last weeks, I have been extensively testing both fugu-mini and fugu-ultra, including day-to-day coding and within the ShinkaEvolve harness. All with great results! Check it out and sign up for the beta testing. We’re launching the beta for our new commercial AI product: Sakana Fugu 🐡, a multi-agent orchestration system! Blog: https://sakana.ai/fugu-beta Fugu hits SOTA on SWE-Pro, GPQA-D, and ALE-Bench, and has been our internal secret weapon. It dynamically coordinates frontier models,…

Related

Source: David Ha (X) | 2026-04-24

Loading related sources…