Research Notes
Working notes from building agentic systems under discipline. These documents were produced by LLMs as part of the research process. They have not been independently verified. They are starting material, nothing more.
The value isn't in the analysis — it's in what the analysis was built on: 208 session decisions, 724 commits, and a human who kept saying "no, that's not right" until it was.
LLM Verification Phenomena
What the Literature Says
What happens when LLM-generated tests pass for the wrong reason, automated reviewers find different bugs on every pass, and the fix-review loop refuses to converge. A survey of what academia knows, what it doesn't, and where our daily practice sits in the gap.
read →The Fight Card
Human vs. LLM Confirmation Bias
16 rounds where the human pushed back against sycophantic drift across 208 session decisions. Mapped from the actual decision record — not reconstructed from memory. Key finding: human won every round by being honest when the model couldn't be.
read →Prospective Metacognitive Regulation
Engineering Systems as Cognitive Scaffolding
The engineering work IS the prospective regulation — not post-hoc analysis of it. The governance systems map onto distributed cognition research in ways I didn't plan. Hutchins' foundational work was literally a study of naval navigation.
read →Metacognitive Analysis
Clinical Psychology of the 16 Pivots
Three-stage clinical psychology analysis of the reflective functioning that enabled each pushback moment. Initial assessment: RF 6-7. Recalibrated to RF 6-9 after disclosure of 20 years meditation practice including 15 Zen sesshin. Three peaks at RF 8-9.
read →