Hi, I'm Steve I have spent the last 30 years making pixels on a screen change color, mostly because I enjoy it but also because people pay me. I start...
The Story I learn by doing, so I decided to learn LLM's by figuring out how to compress one by vibe coding real implementations of things I found in research papers. Project WIZORB identified something interesting about the nature of transformer based large language models. Namely, that much of the strong Universal Weight Subspace Hypothesis (UWSH) seemed not to be real, or at least not to be…
The Story I learn by doing, so I decided to learn LLM's by figuring out how to compress one by vibe coding real implementations of things I found in research papers. For the first challenge, I decided to investigate the Universal Weight Subspace Hypothesis (UWSH) and try to determine if it was valid empirically. The papers authors have had a "Code Releasing Soon" badge on the Github for way too…
Determinism LLMs are stochastic. That’s not a flaw in the design, it’s literally the point. If you ask for the same thing twice you will probably get two different answers, two different implementations, and two different interpretations of what you meant. The vibe coders problem, of course, is that software is expected to be deterministic. Users want the same input to produce the same output.…