Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Lab

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

saved by

• Jaclyn
• Elizabeth Qiu
• Ratan Kaliani
• Emma Guo
• Samuel Lo
• Rishi Kothari
• anka hu
• Information Flow
• Uzay Girit
• Thu Than
• Lydia Nottingham
• Jirat C

related reading

• The Future Worth Building Is Human - Thinking Machines Labthinkingmachines.ai
• Announcing Interactivity Research Grants - Thinking Machines Labthinkingmachines.ai
• Today, we are releasing a research preview of our user model, along with a set of evaluations designed to measure how faithfully user models capture human behavior.persimmon.humansand.ai
• Tiny Interaction Models - Rajan Agarwalrajan.sh
• Training and Evaluating User Language Modelsarxiv.org
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org
• Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
• Together AI | The AI Native Cloudtogether.ai
• Interpretability Infrastructure at Frontier Scale: Harvesting Activations from a Trillion-Parameter Modelgoodfire.ai
• M*: A Modular, Extensible, Serving System for Multimodal Modelsai.stanford.edu
• A Pragmatic Vision for Interpretability — LessWronglesswrong.com