Ex-Yahoo search veterans launch Hornet: agents becoming retrieval's new user
jobergum · x · 2026-11-21
Jo Kristian Bergum and Henning Baldersheim, with nearly two decades building search at Yahoo, explain why they founded Hornet. Their core observations: making retrieval relevant is hard, and scaling retrieval workloads is hard—ranking changes can increase compute while query-cost limits constrain which documents get scored. Hornet unifies retrieval methods, ranking, and scalable execution in one runtime that developers and agents can configure, evaluate, and improve. They argue agents becoming the user of retrieval is the biggest shift of their working lives.
Related event: Vespa co-founders launch Hornet, retrieval infrastructure for agents(2 posts)→
More from coding & agent
- OpenAI details when Ultrafast speed on GPT-6.2 is worth it for rapid iteration — OpenAIDevs · 2026-11-21
- Agent swarm builds ice-flow PDE solver, discovers glacier sliding law beating textbook models — DynamicWebPaige · 2026-11-21
- Paradigm CTO: be unreasonably ambitious with AI — rewrite your whole dependency stack in days — nptacek · 2026-11-21
- Tip: Add Antigravity to your phone's home screen for remote control of all agent threads — amankhan · 2026-11-21
- The sentences your customer-facing AI agent must never say—and how to test for them — rcleffke · 2026-11-21
- Haijun Xia pushes back on 'UI is dead': chat is a UI too, and far from sufficient — sh_reya · 2026-11-21