Notes, mostly on systems, verification, and faithful LLM systems—the data of my thoughts. Some are half-formed; that is the point.
- Skin in the Game When everything can be generated, the last valuable thing is a claim you pay for
-
The Three Pillars of Research Taste, execution, communication—and why a PhD is still an apprenticeship
- Good Ideas Are Rare; Taste Is the Search The first pillar—how to tell good work from bad, and how to make more of the good
- Execution: The Idea Is the Easy Part The second pillar—turning a judged idea into a real thing that works
- Communication: Standing Where the Other Stands The third pillar—moving the work out of your head and into other heads
- Generation Got Cheap. Judgment Didn't. Why I’m blogging again
- Correctness Without a Reference Existential equivalence: a definition of correctness for AI
- Hello, and what this is