Methodology
How to tell whether a result is real, and how to build the tools that check it.
5 essays, newest first
- The Infinite Review Every AI reviewer finds one more critical finding, because finding problems looks like work. The bias is human first. The fix is not a better prompt, it is a file: how we gave our reviews a terminal state.
- Your Notes Are Not the Deal My overnight agent called two live deals dead because it read my folders, not the deal. Why a self-kept record goes quiet exactly where the work is hottest.
- ZCoP: The Plan That Rewrites Itself Zero Chain of Prompt (ZCoP), a planning template for LLM work: draft the whole roadmap as a table, trust only the next step, rewrite it after every step.
- The Next World to Build Last time, my digital organisms hit a wall: they die too young to ever see a season change. Here is how I went looking for the fix, and why I measured the disease carefully before touching the cure.
- The Bug That Caught Me Cheating I added scavengers to my evolving world and it worked perfectly, which is exactly how I knew something was wrong. A short story about the one test I now trust to tell whether a behavior really evolved or whether I quietly programmed it.
