What Building Self-Hosted LLM Systems Taught Me About Software

overview I figured the reasoning capabilities would lend themselves to chess, and they do. Right now I am limited by the 50 o1-preview requests I have to do research in this area so keep this mind when I share. testing vs stockfish I was playing o1-preview against stockfish (via lichess), and it held up for the most part, but stockfish was...

purpose Physicists long balked at colloquial usages of “entropy” (especially by philosophers). I believe some usages of entropy as resistance to systematic understanding has precise mathematical grounding in information theory. I am tired of arguing with my physics major friends over this. definitions Shannon entropy H(X) for discrete random...

premise After I saw that Github Copilot was able to do my DSA coursework with little guidance (though, I never did use it to cheat) I for sure thought that LLMs would ruin kids ability to learn how to code and that it would handicap their learning of not only coding but the meta-cognitive skills around learning coding (ie, “learning how to...

clarification What I mean is that, conceptually, “MOATs” are not a useful abstraction. There is a saying that “all models are wrong, but some are useful” and I am saying that, as a model, MOATs are not useful. I think that asking a founder “what their MOAT is” will not offer useful information about their project. I am also specifically...

the analogical physics of creativity Consider paint mixing: two colors swirling together create temporary, unrepeatable patterns. These patterns exist only in transition—between separation and uniformity, in a parallel to mental states. Like those paint swirls, certain cognitive configurations exist only in transition, in states of productive...