Models & Labs
OpenAI Codex Goes Mobile in ChatGPT App
The Rundown AIhigh confidence
Why it matters
- →OpenAI's mobile integration enhances developer flexibility by allowing task management on the go.
- →The secure relay layer ensures safety without exposing devices to the internet.
- →This move intensifies competition in the AI coding tool market, challenging Anthropic's offerings.
OpenAI has rolled out Codex within the ChatGPT iOS app, enabling developers to manage AI coding tasks from their mobile devices. This integration allows users to approve decisions, initiate new tasks, and monitor ongoing processes without being tied to a computer. The system employs a secure relay layer to maintain security while syncing with other ChatGPT instances. This move positions OpenAI against Anthropic, which has also been enhancing mobile capabilities for AI task management. The update offers developers greater flexibility and convenience, marking a shift in how AI coding tasks can be managed.
Read originalMore from The Rundown 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.
