A developer built a private health consultation bot that runs entirely in the browser using WebLLM and WebGPU, eliminating the need for backend servers and ensuring zero data leakage. The system execu…
Researchers have developed a new structured pruning method for large language models that borrows from unstructured Adaptive Feature Retention, addressing distribution mismatches, sign information los…
Researchers proposed a structured pruning method for large language models that combines power transformation, sign-preserving score aggregation, and adaptive feature retention. Tested on Llama-3-8B, …
A developer built a privacy-first health pre-diagnosis system using MLX Swift and a quantized Llama-3-8B model on iOS. The system runs entirely on-device, ensuring 100% data sovereignty by processing …
Microsoft's MDASH, a multi-model agentic scanning system, has moved from research to production, actively finding vulnerabilities in Windows, Azure, and identity engineering workflows. It discovered 1…
Researchers introduced AgenticInterpBench, a benchmark for circuit explanation in mechanistic interpretability, and HyVE, an agentic explainer that uses language models to analyze transformer circuit …
The U.S. Department of Commerce's ban on Anthropic's Claude Fable 5 and Mythos 5 models over autonomous zero-day discovery concerns is counterproductive for cloud security, according to a cloud engine…
Researchers have developed SERC, a semantic error correction framework inspired by LDPC codes that treats LLM text generation as a noisy communication channel to detect and fix hallucinations. The tra…