Ollama's MLX engine has been updated to deliver its highest performance on Apple Silicon yet. By leaning more heavily on Apple's unified memory and the Metal-backed MLX framework, models output higher quality responses, respond faster, and use less memory. The update includes support for NVFP4 format, up to 20% faster output, and a snapshot system for agent workflows.

This article is the second part of the PyTorch profiling series, delving into the internals of nn.Linear layers, including transpose operations, bias-fused epilogue techniques, and the impact of torch.compile on a single linear layer. It then dissects the performance characteristics of a Multilayer Perceptron (MLP) with GeGLU activation, showcasing the scheduling and execution of GPU kernels.

Release of datasette-agent 0.2a0 with new user interaction and query saving capabilities.

Google has released DiffusionGemma, a new open-weight model under Apache 2 license, available for free via NVIDIA's NIM cloud API. It delivers impressive generation speeds exceeding 500 tokens per second.

As robotaxi services expand globally, NVIDIA introduces Halos OS—a comprehensive safety system integrating certified OS, standardized interfaces, AI guardrails, and a validation framework to ensure safety is built into autonomous vehicles from the ground up.

Google researchers introduce Regularized f-Divergence Kernel Tests to audit machine unlearning and privacy. The framework adaptively selects optimal divergence measures, improving detection of data leaks and unlearning failures while requiring fewer samples and less tuning.

Google DeepMind released DiffusionGemma, an experimental open model for fast text generation using parallel token generation. NVIDIA optimized it to run faster on GeForce RTX, RTX PRO, and DGX Spark systems, achieving up to 1000 tokens/sec locally.

Install and configure LSP servers for GitHub Copilot CLI, replacing brute-force grep/decompile with real code intelligence. The LSP Setup skill automates the process, supporting 14 languages. This post explains how it works and how to get started.

AWS announces Neuron Agentic Development, a set of AI agents and skills that enable developers to author, debug, and optimize custom kernels for Trainium and Inferentia without deep hardware expertise, significantly reducing development cycles.

Jeremy Howard proposes a simple solution to slow down recursive AI self-improvement: the lab with the top-ranked model must agree not to use it for frontier AI research, but everyone else should have access. This prevents frontier advancement and power imbalance. He criticizes Anthropic for doing the opposite.

This tutorial shows how to build an AI-powered equipment repair assistant using Amazon Bedrock AgentCore, helping farmers and field technicians diagnose problems, identify parts, and access repair procedures via natural language. The solution uses AgentCore Runtime with Strands Agents SDK, Amazon Nova 2 Lite as the foundation model, Amazon Bedrock Knowledge Base for RAG, and AgentCore Memory for conversation persistence.