I've been obsessively tinkering for weeks on Daimon, my pet little non-LLM AI realtime cognitive machine. Still trying to figure out what it can actually achieve besides be a massively fun time sink for me.

~32,500 lines of Zig written with me at the helm of Claude Code.

More research than I can even fathom across computer science, cognitive science, neuroscience, and more. As the post points out - I've lost the ability to actually reason about what is going with its internals. I'm just the high-level architect making suggestions at this point.