About

I'm Jiří Klimeš, a software engineer by trade, and in my own time an ML researcher by stubbornness. One idea holds most of my attention: today's models are artificial intuition. Recognition is fast and cheap, and it stops at the boundary of the known. Past that boundary the only tool left is search, and making search fast is the actual problem.

I taught myself to code out of boredom on a vacation: one eight-hour Python video, then a long stretch of tutorials. I climbed out by building things I actually wanted. A notification when my parents' phones hit the home wifi so I knew to look busy. An auto-ordering script for school lunches. A timetable app in Flutter for my class.

Then a friend asked whether neural nets would be hard, and we found out the slow way. We generated datasets of logic ops and addition and trained a single perceptron on them with random mutation. It got stuck on XOR, which is how we learned we needed layers. Then genetic algorithms evolving a population of Snake-playing agents, and finally we cracked backprop. Only after that did we touch Keras, then switched to JAX, writing our own CUDA kernels along the way. Digit classification, stable diffusion from scratch, anomaly detection built from our own ideas, transformers at small scale. When the ARC-AGI prize was announced I spent three months on it. Between that and Chollet's paper On the Measure of Intelligence, it clicked: models trained to recognize don't learn to reason, and scale wasn't going to change that. So I went back to first principles, and that became light-search.

The plan, stated plainly so I can be held to it: build an assistant that compounds how fast I learn and build. Use it to help build real intelligence, then aim it at aging: epigenetic reprogramming and the hallmarks, pushed far enough to reach rejuvenation and buy us time. Use the time to make the mind substrate-independent, then go see the universe.

Email is best.