Writing

Failure Notes: How to Run an LLM on a User Laptop

Users refuse to send documents out, so we ran the model on their own machines, and one document evaluation took 23 minutes on an office laptop. With no GPU, growing the model and shrinking it are both blocked, so we went with a small model, removed JSON, and enforced format with a grammar. Implementing that, we got stuck six times and the cause was our code every time. What raised processing speed by 10x was one option that fetched a full probability distribution every token and then threw it away.

Finding the Problems Where Capital Doesn't Decide

My founder friend said our Indic LLM story sounded two years old next to physical AI. The useful work was not chasing a fashionable comparable. It was killing wrong prescriptions until the only remaining space was hardware-constrained inference, evaluation that spends test once, and products that compound from owned usage.

Don't Start a Business

New Year brought a wave of questions about whether to found something. I am only nine years in. I do not have much to offer except this: do not. The numbers say stop. The contradiction is that I would start again for the co-founders I had.

Pascal: no time to make it shorter

AI made long drafts cheap and noisy while reading time stayed fixed. Use models to think and explore, then force every thread into one page colleagues can finish without hunting for the point. The Claude skills linked here enforce that cut.

Matrix OS: a twin that does not die

Soul OS, Matrix OS, and Matrix as a Service: from The Matrix to environments where digital twins interact. The aim is a persistent replica that stores experience in real time, a society those Souls inhabit, and shared rooms for safety and system-dynamics research.

Manifesto: freeing others as I was freed

Why I will pursue wealth and influence: to fund a school, a hospital, and orphanages. Capital and authority are instruments; the purpose is to free others from avoidable hardship the way education freed me, then sustain those institutions so the obligation outlasts any one company.