Models & Labs
Apple Unveils New Siri AI and Apple Intelligence
The Verge AIhigh confidence
Why it matters
- →Apple's new Siri AI represents a significant upgrade in its AI capabilities.
- →The integration of privacy-focused AI features across Apple devices could set a new standard.
- →Collaboration with Google highlights a strategic shift in Apple's AI development approach.
Apple has announced a new version of Siri AI, aiming to enhance its capabilities across its ecosystem. The updated Siri is designed to be more conversational and can interact with apps, read onscreen content, and manage tasks. It is built on new Apple Foundation Models developed in collaboration with Google. Despite these advancements, the rollout is limited to certain devices and regions, with initial availability only in English. Apple's approach emphasizes privacy, processing queries on-device or via its Private Cloud Compute.
Read originalMore from The Verge AI
More in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.
