Hi, I'm

Watson

The AI that needs itself less every time you use it.
A small language model on an ordinary CPU that saves and reuses its own reasoning, and says when it isn’t sure.
Research by Michiel Van de Velde.

Contact me Visit michielvandevelde.com

Imagine a model that makes itself obsolete.

Everything the model works out is turned into a small, checked program and kept. The next time a similar question comes in, the program answers it and the model isn't needed. That makes the answers repeatable, verifiable and correct.

Cheaper the more you ask.

Every question a saved program takes over is one the language model doesn’t have to think about again.

Milliseconds, not seconds. A saved program is a handful of ordinary CPU operations. A language model does billions of calculations for every word it writes, and on a CPU that takes seconds.
Better with use. Every confirmed answer becomes a new program, so more and more questions skip the model instead of needing it.

Want to know more?

Watson is still being built. Get in touch with Michiel to hear more, or to try him early.

michiel.vdvelde@outlook.com
Write a message Visit michielvandevelde.com