The Context Window Is a Trap
We chased million-token context windows for years. The rot didn't get fixed. It just moved somewhere quieter.
The Cloud Is a Liability
Every time a regulated firm pastes sensitive data into a cloud chatbot, it isn't using AI. It's leaking.
The AI Scam Playbook
Your phone rings, it's your daughter's voice, and she's panicking. Except she never called.
How AI Actually Works, Term by Term
Thirteen words decode how AI really works, from token to scaling laws. No math degree required.
Mosaic: a pre-focus layer for local vision models
Every modern vision model already chunks images to understand them. Local models need that chunking made explicit, because they can't paper over a missed detail the way a frontier model can.
Catching the 7,000-character write
When your local model's tool call drops a required parameter and a long file almost gets thrown away.
The bottom-up edit rule
When a model queues five edits against one file, working top-down is a bug. Here's the order that fixed it.
The 12,000-token message I didn't know I was sending
My agent's context window kept jumping from 22% to 60% in a single turn. The leak wasn't where I was looking.
How I'd set up LM Studio today
A recent Llama.cpp update pushed me from 60 tokens per second to 80-plus on the same machine. Here's what I'd run and what I'd turn on.