✳flâneur — a map of the web's best reading
Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Lab
thinkingmachines.ai · 3,854 words · saved by 18 readers
Interaction models move beyond turn-based AI interfaces by handling multimodal, real-time collaboration natively across audio, video, and text.
Today, we’re announcing a research preview of interaction models: models that handle interaction natively rather than through external scaffolding. We think interactivity should scale alongside intelligence; the way we work with AI should not be treated as an afterthought. Interaction models let people collaborate with AI the way we naturally collaborate with each other—they continuously take in audio, video, and text, and think, respond, and act in real time. We train an interaction model from scratch. To ensure real-time responsiveness, we adopt a multi-stream, micro-turn design. Our researc
Explore this link on the map →saved by
- Jaclyn
- Elizabeth Qiu
- Ratan Kaliani
- Emma Guo
- Samuel Lo
- anka hu
- Uzay Girit
- Thu Than
- Jirat C
- Sebastian J Zhao
- Timothy Kostolansky
- Kushal Thaman
related reading
- The Future Worth Building Is Human - Thinking Machines Labthinkingmachines.ai
- Announcing Interactivity Research Grants - Thinking Machines Labthinkingmachines.ai
- Advancing voice intelligence with new models in the API | OpenAIopenai.com
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- Ultra Instinct | Eric Jangevjang.com
- Crossing the uncanny valley of conversational voice | Sesamesesame.com
- Improving Composer through real-time RL · Cursorcursor.com
- Real-Time Action Chunking with Large Modelspi.website
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- [2505.10831] Creating General User Models from Computer Usearxiv.org
- Modeling natural conversational dynamics with Seamless Interactionai.meta.com
- Redirecting...si.inc