The Facts
Straight Info
Plain-language guides to how AI actually runs: where the work happens, what a model remembers, what it invents, and what the electricity is for. The Violet Echoes pages are examples. They are not the evidence.
Why local AI matters
Edge computing vs. the cloud
Edge computing does the work near the data. A cloud does it in a distant building. Most real systems use both. The choice is where the wait, the power bill, and the copy of the data should live.
What a model actually keeps
How AI memory works, and why it forgets
A chat model does not remember your life by default. It sees a limited window of text. When that window fills, the start falls out unless something else saved it.
Training is a spike. Answers are the bill.
The energy cost of AI
Training a large model spends a great deal of electricity once. Every reply after that spends more. Cooling the building is part of the same bill. Efficiency is a design choice.
Local is a place, not a virtue
Running a model on your own machine
A local model is a file of weights on a computer you control, plus a program that runs them. The prompt stays there unless some other app sends it out. The electricity still comes out of the wall.
Fluent is not the same as true
Why a model invents an answer
A language model continues a pattern. A sure-sounding sentence is one of the patterns it learned. If the true answer is not in what it can see, it will often finish the sentence anyway.
Chips that fire when something happens
Neuromorphic hardware
Ordinary chips grind through dense math on a clock, whether the input changed or not. Neuromorphic chips take a different bet: do the work as sparse events, closer to how a neuron spikes, and spend less when the world is quiet.
Six pages. Each one is an explanation, not a stub. The City links are examples, not proof. Enter the City if you wanted the island instead.