Sakana Fugu

	Sakana Fugu(sakana.ai)
	228 points by Finbarr 1 day ago \| 119 comments
	tl;dr: Sakana AI launched Fugu and Fugu Ultra, a multi-agent system delivered via an OpenAI-compatible API that dynamically orchestrates a pool of frontier models (selecting roles like Thinker, Worker, Verifier) based on two ICLR 2026 papers (TRINITY and Conductor). The company claims benchmark results matching or exceeding GPT-5.5, Opus 4.8, and Gemini 3.1 Pro on coding, reasoning, and agentic tasks like SWE-Bench Pro and TerminalBench. Pricing starts at $20/month, with Fugu Ultra at $5/$30 per million input/output tokens; it's unavailable in the EU/EEA pending GDPR compliance.
	HN Discussion: ~Founder has strong credentials but this specific product seems poorly thought out ↓Product is too slow, expensive, and limited to be a viable daily workhorse compared to competitors ↓Technical report shows minimal improvement from the orchestrator over base models ↑Multi-model routing/checking is a smart strategy and the product delivers on complex tasks ↓Skepticism that this actually solves single-vendor dependency or justifies stacking another subscription