AI & Tech

In this tutorial, we work through an end-to-end workflow for Qualcomm AI Hub Models. We start by setting up the required package, discovering the available model collection, and loading MobileNet-V2 for local PyTorch inference. We also handle an important input-shape issue by converting NHWC image tensors into the NCHW format expected by the model. From…

As public backlash to the seeming omnipresence of artificial intelligence intensifies, the collective quest to weed out—and reject—telltale signs of its use continues. One of the first casualties, to my dismay, was em dashes—which are a great, and very human form of punctuation, by the way! There’s also the “rule of threes,” which is meant…

Asking venture capitalists for investment is a rite of passage for tech founders. This has led to another universal experience: the VC pitching horror story. A massive conversation sharing such stories has taken place all week on X with the comments both funny and infuriating. We read through them all to find the most interesting…

Google DeepMind released Quantization-Aware Training (QAT) checkpoints for the Gemma 4 family. The release targets local deployment on edge devices and consumer GPUs. It follows the Gemma 4 launch in April and a 12B model two days earlier. We compared the available Gemma 4 edge-model formats using only published numbers. The goal was simple. Show…

Perplexity AI announced what it calls the first hybrid local-server inference orchestrator at Computex 2026. The system is designed to automatically route AI tasks between a user’s local device and cloud-based frontier models without requiring the user to decide in advance. The feature is expected come to Perplexity Computer in July 2026. What is Hybrid…