PulseAugur
实时 22:11:23

Thinking Machines Lab unveils real-time multimodal interaction models

Thinking Machines Lab, an AI research lab, has introduced a new class of systems called interaction models designed to overcome the limitations of traditional turn-based AI. These models feature a native multimodal architecture that allows for real-time human-AI collaboration, processing audio, video, and text inputs and outputs in continuous 200ms micro-turns. This approach enables the AI to listen, interrupt, and react proactively, moving beyond static chat interfaces to a more dynamic and integrated interaction. AI

影响 Moves AI interaction beyond static chat interfaces to real-time, multimodal collaboration.

排序理由 Research preview of a new AI architecture from a research lab.

在 MarkTechPost 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

Thinking Machines Lab unveils real-time multimodal interaction models

报道来源 [3]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Mira Murati’s Thinking Machines Lab Introduces Interaction Models: A Native Multimodal Architecture for Real-Time Human-AI Collaboration

    <p>Thinking Machines Lab has introduced a research preview of TML-Interaction-Small, a 276B parameter Mixture-of-Experts model with 12B active parameters, built around a multi-stream, time-aligned micro-turn architecture that processes 200ms chunks of audio, video, and text simul…

  2. Mastodon — fosstodon.org TIER_1 Italiano(IT) · [email protected] ·

    🧠 Thinking Machine, the reality created by Mira Murati proposes a new paradigm for human-AI interaction: models designed to collaborate in real-time. 👉 I

    🧠 Thinking Machine, la realtà creata da Mira Murati propone un nuovo paradigma per l’interazione uomo-AI: modelli progettati per collaborare in tempo reale. 👉 I dettagli: https://www. linkedin.com/posts/alessiopoma ro_openai-ai-genai-activity-7460280291593527296-wN-b ___ ✉️ 𝗦𝗲 𝘃𝘂…

  3. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Thinking Machines Lab is building interactivity into model architecture itself—200ms response chunks across audio, video, text. The shift: from chat interfaces

    Thinking Machines Lab is building interactivity into model architecture itself—200ms response chunks across audio, video, text. The shift: from chat interfaces wrapping static models to systems that listen, interrupt, and correct in real time. This moves the competitive moat from…