Mira Murati's Interaction Models: Full-Duplex AI Responds in 0.4 Seconds

On May 11, 2026, Mira Murati’s Thinking Machines Lab published the architecture behind their first model: full-duplex AI that listens and responds simultaneously, hitting 0.4-second turn-taking latency versus GPT-Realtime-2.0’s 1.18 seconds. Here is what the dual-component architecture actually is, what FD-bench measures, and what developers can build with it now.

Continue reading the full article on WowHow →

Originally published at https://wowhow.cloud/blogs/thinking-machines-lab-interaction-models-full-duplex-ai-mira-murati-2026

Comments

Post a Comment

Popular posts from this blog

How YC Startups Actually Use AI Workflows (Spoiler: It's Not Zapier)

While everyone debates Zapier vs Make, YC startups are quietly building AI workflows that process millions of operations daily. Here's the tech stack they actually use—and why it's nothing like what the productivity gurus recommend. Continue reading the full article on WowHow → Originally published at https://wowhow.cloud/blogs/how-yc-startups-actually-use-ai-workflows
Read more