I ran a seventeen-persona roundtable twice. I discarded almost the entire business track and kept the safety-design track word for word in the spec. I only later realized the line wasn't advice quality, it was identity. Chapter 6.
At first I just thought of it as an interactive edu tool. Then, passing through a domain with no right answer and the LLM's tendency to agree, the name became not a label but a safeguard. Chapter 5 of a serialized notebook.
I set the closest things beside mine to check if the spot was really empty. Where Khanmigo, Replika, and Brilliant part ways, and why the philosophy-chatbot line stays blurry. Chapter 4 of a serialized notebook.
I ran a seventeen-persona roundtable twice. I discarded almost the entire business track and kept the safety-design track word for word in the spec. I only later realized the line wasn't advice quality, it was identity. Chapter 6.
At first I just thought of it as an interactive edu tool. Then, passing through a domain with no right answer and the LLM's tendency to agree, the name became not a label but a safeguard. Chapter 5 of a serialized notebook.
I set the closest things beside mine to check if the spot was really empty. Where Khanmigo, Replika, and Brilliant part ways, and why the philosophy-chatbot line stays blurry. Chapter 4 of a serialized notebook.
After narrowing and paring, what was left fit no category. Too answerless for education, yet the same thing they did at Harvard. Was the blank spot an opportunity or a trap. Chapter 3 of a serialized notebook.
Giving shape to an AI tutor for morality, the first move was deciding what not to build. Why I narrowed to one trolley and shelved subscriptions, typing, K-12, and professional ethics. Chapter 2 of a serialized notebook.
A six-year question that started with the trolley scene in The Good Place. Can AI build a kind of learning that makes people less certain, not more, in domains without right answers. Chapter 1 of a serialized notebook.