In the news
Open d1: Edge decision models for text, vision, and audio
Liquid AI · Published · 3 min read
In 30 seconds
- What happened
- Liquid AI released d1-3B and d1-omni-600M, open-weight decision models that produce single-pass answers for text, vision, and audio without token generation.
- Why it matters
- Engineers building real-time inference systems on edge devices or data centers who need fast structured decisions with multimodal inputs should evaluate these models.
- Watch out
- d1-omni-600M is experimental; audio benchmarks lack standardized evaluation; vision capabilities validated only on standard benchmarks, not the private Decision Index split.
- edge
Who else ran this
- Introducing d1: The most capable decision model, now with visionLiquid AI
- Multimodal open d1 decision models for the edgeHugging Face
The same event, reported by other publishers we follow.
The patterns behind this
- Generative UI (Agent-Rendered Interfaces)
- Agentic Context Engineering (Evolving Playbook)
- Multimodal RAG
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.