A bestiary of AI metaphors Lately, I’ve been thinking about the many metaphors we use as shorthand for describing and understanding large language models (LLMs). Has any technology in the history of humankind amassed such a rich and diverse collection in such a short amount of time? Let’s quickly go through the list: First, the Silicon Valley

Big GPUs dont need big PCs Ever since I got AMD, Intel, and Nvidia graphics cards to run on a Raspberry Pi, I had a nagging question: What’s the point? The Raspberry Pi only has 1 lane of PCIe Gen 3 bandwidth available for a connection to an eGPU. That’s not much. Especially considering a modern desktop has

Reflections on AI at the end of 2025 For years, despite functional evidence and scientific hints accumulating, certain AI researchers continued to claim LLMs were stochastic parrots: probabilistic machines that would: 1. NOT have any representation about the meaning of the prompt. 2. NOT have any representation about what they were going to say. In 2025 finally

Your job is to deliver code you have proven to work

15 TB of VRAM on Mac Studio - RDMA over Thunderbolt 5 Apple gave me access to this Mac Studio cluster to test RDMA over Thunderbolt, a new feature in macOS 26.2. The easiest way to test it is with Exo 1.0, an open source private AI clustering tool. RDMA lets the Macs all act like they have one giant pool of

Plugins case study mdBook preprocessors

Gemini 3 Flash

I ported JustHTML from Python to JavaScript with Codex CLI and GPT-52 in 45 hours

Happy Chanukah This (taken in Kiel, Germany in 1931 and then colorized) is one of the most famous photographs in Jewish history, but it acquired special resonance this weekend. It communicates pretty much everything I’d want to say about the Bondi Beach massacre in Australia, more succinctly than I could in words.

JustHTML is a fascinating example of vibe engineering in action