Models & Labs
Thinking Machines Develops Real-Time AI Interaction Models
The Verge AIhigh confidence
Why it matters
- →Interaction models could revolutionize human-AI collaboration by enabling real-time, multi-modal communication.
- →This approach addresses the current limitations of AI's single-threaded interaction, potentially increasing the effectiveness of AI applications.
- →The development signals a shift towards more intuitive and responsive AI systems, aligning them closer to human communication patterns.
Thinking Machines, an AI company founded by ex-OpenAI CTO Mira Murati, is developing 'interaction models' to enhance real-time collaboration between humans and AI. These models aim to process multiple modalities like audio, video, and text simultaneously, allowing for more natural and responsive interactions. The company plans to release a limited research preview in the coming months, with a wider rollout expected later this year. This development could redefine how AI systems interact with users, making them more intuitive and effective.
Read originalMore from The Verge AI
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.
