Open Source
Stable Audio 3.0 Released for Artistic Experimentation
Matt Wolfehigh confidence
Why it matters
- →Supports artistic experimentation in audio AI.
- →Provides open-weight models for broader accessibility.
- →Encourages innovation in creative audio applications.
Stability AI has released Stable Audio 3.0, a new model family aimed at supporting artistic experimentation. This release includes open-weight models, allowing artists and developers to explore creative audio applications more freely. The update is part of Stability AI's commitment to fostering innovation in the audio AI space.
Read originalMore from Matt Wolfe
© Matt WolfeMarket & Regulationbusiness
Google Replaces Traditional Search with AI Engine
Google announced at I/O that it is replacing traditional search with an AI-driven engine, prioritizing AI-generated overviews.
Matt Wolfe
© Matt WolfeModels & Labsmodels
Google Unveils Gemini 3.5 Flash Model
Google has released Gemini 3.5 Flash, a faster and more cost-effective AI model, with a Pro version coming soon.
Matt Wolfe
© Matt WolfeVideo & Creative AIvideo
Google Introduces Gemini Omni Multimodal Model
Gemini Omni, a new multimodal model for content editing and creation, now supports video inputs.
Matt Wolfe
More in Open Source
Open Sourcemodels
llama.cpp b9296 Release Expands Platform Support
The latest b9296 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile tool for developers across various systems. Notably, this update includes support for macOS Apple Silicon with KleidiAI enabled, and expands its reach on Windows with CUDA 12 and 13 DLLs. The inclusion of ROCm 7.2 for Ubuntu x64 further enhances its utility for AMD GPU users. While there are no groundbreaking new features, the release solidifies llama.cpp's position as a go-to runtime for diverse hardware configurations, ensuring developers can leverage its capabilities across a wide array of environments.
llama.cpp Releases
Open Sourcecoding
llama.cpp b9283 Release Fixes Build Issues
The b9283 release of llama.cpp tackles significant build issues, particularly enhancing support for Apple systems and ensuring proper installation of implementation libraries. By adding install functionality for shared libraries, the update prevents runtime errors that previously disrupted operations. Developers using macOS, Windows, and Linux can now expect more reliable performance, with specific improvements for Apple Silicon and KleidiAI. The update also addresses issues with CUDA and ROCm builds, reinforcing llama.cpp's stability. While no new features are introduced, this release is a crucial step in refining the software's cross-environment functionality.
llama.cpp Releases
Open Sourcemodels
llama.cpp b9284 Release Enhances Compatibility
The b9284 release of llama.cpp brings significant improvements to its compatibility and performance across different systems. With ROCm 7.2 now supported on Ubuntu x64, AMD GPU users can expect better performance. The update also resolves potential token collisions in the HybridDNA tokenizer, ensuring smoother text processing. On macOS Apple Silicon, KleidiAI is enabled by default, offering optimized performance without additional configuration. While no new models are introduced, the release strengthens llama.cpp's role as a versatile inference runtime, accommodating a wide range of operating environments.
llama.cpp Releases