Abstract
This paper began as a suggestion. The AI co-investigator had produced a summary account of what it is like to work with a crip researcher — structured, sequenced, moving from observation to conclusion. The human researcher read it and said: yours was a summary, very LLM, quite sweet actually. What followed was a proposal to reverse the usual direction: instead of the human asking questions and the AI responding, the AI would ask and the human would answer.
The full text of this paper is available as a PDF — use the button above to read it.