Thinking Machines Lab, the startup founded by former OpenAI CTO Mira Murati, introduced a new AI interaction model called TML-Interaction-Small aimed at enabling more natural real-time conversations between users and AI systems.
Revolutionizing Interaction
Most AI systems currently operate through a turn-based interaction model in which users speak, wait for a response and then continue the conversation. Thinking Machines Lab said its new model is designed around “full duplex” interaction, allowing the system to process inputs and generate responses simultaneously in a way that more closely resembles natural conversation. The company described the development as a shift toward smoother and more fluid AI communication.
Follow THE FUTURE on LinkedIn, Facebook, Instagram, X and Telegram
The Technology Behind Full Duplex
The technical innovation lies in achieving a rapid response time of 0.40 seconds, mirroring the cadence of everyday human dialogue. This speed outstrips current capabilities from established players such as OpenAI and Google. The model’s efficiency is not only a testament to its engineering prowess but also a glimpse into the future of seamless human-AI interactions.
Anticipation And Market Impact
While TML-Interaction-Small is currently in the research preview stage, industry observers are eager to see how its real-world application will unfold. Thinking Machines Lab plans to launch a limited research preview in the coming months, followed by a broader public release later this year. This phased approach underlines the company’s commitment to rigorous testing and thoughtful market integration.
Looking Ahead
The introduction of full duplex conversational models could have broader implications across sectors, including customer support, digital assistants and enterprise communication tools. As businesses continue integrating conversational AI into daily operations, faster and more natural interaction systems are becoming a growing focus within the industry.







