Models & Labs
Viture Launches Privacy-Focused AI Glasses
WIRED AIhigh confidence
Why it matters
- →Viture differentiates from Meta by using bone-conduction audio instead of cameras, addressing major privacy concerns.
- →The device aggregates multiple LLMs (Claude, Gemini, ChatGPT) to build a personalized memory graph rather than just recording transcripts.
- →At $299, it offers a lower-cost entry point into the smart glasses market compared to many camera-equipped competitors.
Viture has announced Vonder, a new line of smart glasses designed to map users' memories and thoughts via audio rather than video. Unlike competitors such as Meta’s Ray-Ban glasses, Vonder lacks cameras, relying instead on bone-conduction sensors and microphones to capture speech passively. The device integrates with multiple large language models, including OpenAI’s ChatGPT and Anthropic’s Claude, to create a personalized 'memory graph' of the user's life. Priced at $299, the glasses feature bone-conduction audio for calls and music, with preorders opening September 28 and shipping in November. The company positions the product as a privacy-first alternative to camera-equipped wearables, targeting users concerned about being recorded by others.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from WIRED AI
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
