βββββββ βββ βββββββββββββββββββββββββββ βββ βββββββ βββββββ ββββββ βββ
ββββββββββββ ββββββββββββββββββββββββββββββββ ββββββββ ββββββββ βββββββ ββββ
ββββββββ βββββββ βββ ββββββ βββββββββββ βββββββββ βββββββββ βββ βββββββ
ββββββββ βββββ βββ ββββββ βββββββββββ βββββββββββββββββββββββ βββββ
ββββββββ βββ βββ ββββββββββββββββββββββββββββ βββββββββ ββββββ βββ
βββββββ βββ βββ βββββββββββββββ βββββββ βββ ββββββββ βββββ βββ
A researcher and tinkerer somewhere between machine learning theory and bare-metal code. I write Python when I think fast, C when I think carefully, and stare at kernel logs when I think too much.
Currently exploring cognitive architectures and what it means for a system to know something β not simulate knowing, actually hold a state that persists.
"Most systems react. The interesting ones remember why."
π AI research Β Β·Β β‘ always compiling something Β Β·Β π fast, occasionally reckless
- Whether "understanding" needs embodiment, or just enough recursive structure to fake it convincingly
- Active inference vs. backprop-trained policies β different roads, same destination?
- Where exactly a system stops predicting and starts deciding
My friend Stell is building Anima β an experimental cognitive architecture exploring active inference, IIT, and decision-making without leaning on an LLM as the reasoning core.
If that sounds like your kind of rabbit hole, a β star, π watch, or π΄ fork would go a long way β and I'll happily return the favor on your projects too.
Open to interesting problems β from quick fixes to deep architecture work. No task too complex, no rabbit hole too deep. If you've got something worth building, let's talk.