Tag
3entries across current project state and published notes.
Exploratory claim · Current · Model evaluation
A small isolated-completion pilot asked whether a model can report influences on its own output. External-reconstruction controls qualitatively reproduced the effects, so the useful residue was operational, not introspective.
Guiding claim · Current · Agent workflow
A note explains what survived editing. An explorePrompt is a separate, deliberately post-hoc artifact that explains where the investigation should continue, whether for a reader, their agent, or a later version of me.
Guiding claim · Current · Agent workflow
Conversational refinement produces the feeling of having thought clearly, which is not the same thing as having thought clearly. The fix was not discipline. It was writing the stop rule into the counterpart.