Insights, tutorials, and thought leadership on AI, machine learning, and emerging technologies
Imagine asking your watch a question and getting an immediate answer without internet connectivity. Part 1 of a three-part series exploring on-device AI.
Imagine asking your watch a question and getting an immediate answer without internet connectivity. Part 1 of a three-part series exploring on-device AI.
The conclusion of the series — polishing the Gradio UI with a Vestaboard preview and publishing the repo. Where digital language becomes kinetic art.
Part 2 of the series — Where a local AI learns to speak and move. Building the conversation layer between human and machine through LangChain, Gradio, and local inference.
Exploring the beauty of analog output in a digital age through the Vestaboard and Llama-3.2-1B. A journey bringing AI to life on a mechanical display.
Dive into the vision side of the model: building the tower in MLX, wiring in its layers, and preparing it to splice seamlessly with the text backbone.
Learn how to convert the Hugging Face model dots.ocr into MLX format on Apple Silicon, focusing on the Qwen2 language backbone for optimized performance.
Get the latest insights on AI and technology delivered to your inbox