What GraphRAG is, why vector search alone falls short, and when you'd actually reach for it.
Photo: Jordan Harrison
LM Studio 0.4.0 extracts the inference engine into a standalone headless daemon with a full CLI and an Anthropic-compatible endpoint, meaning you can point Claude Code at a local model by setting two environment variables.
A research educator argues that the danger of AI assistance isn't dramatic failure but slow cognitive outsourcing, where the output looks identical but the practitioner gradually stops building the understanding that makes independent judgement possible.
Nanocode demonstrates training a 1.3B parameter Claude Code-style coding agent from scratch -- pretraining, supervised fine-tuning, and preference optimisation -- on a TPU v6e-8 for around $200 in under nine hours.
Tim O'Reilly profiles Harper Reed's argument that AI-speed iteration cycles destroy the feedback loops through which product teams build conviction, requiring new frameworks for decision-making under permanent optionality.
Minor Component Adaptation targets low-variance singular subspaces rather than dominant ones, achieving up to 5.9x more knowledge acquisition than LoRA using a fraction of the parameters.
Tiny Corp's TinyGPU DriverKit extension, now officially signed by Apple, brings Nvidia Ampere and AMD RDNA3 eGPU support to Apple Silicon Macs without requiring SIP bypass -- the first time Nvidia hardware has ever had official macOS support.