Potential improvements to HowTruthful and its agent skills

by Bruce R. Lewis

revisions

2 min read

HowTruthful

I followed my own instructions for exploring Massachusetts 2026 ballot question arguments. I figured out how I want to vote. I also figured out some improvements to make to HowTruthful and its associated skills.

  1. Since users are rating statements' truthfulness on a 1-5 scale, it's not very useful to have a hedged statement like "Massachusetts legislators who run unopposed can take voters for granted and ignore important issues." If the rest of the statement is even a possibility, the word "can" makes the statement as a whole true. The AI skill should change such statements into a definitive form like "Massachusetts legislators who run unopposed will take voters for granted and ignore important issues." Then the user can rate that statement false, dubious, debatable, plausible, or true.
  2. There was a contest where I was among the winners, even though I disagreed with the organizers' vision of having AI assess truthfulness. In my contest entry I opined that humans should do the final assessment; AI's role would stop at ingesting and structuring arguments. (More on the contest in a future post.) Having just gone through 400 or so statements in order to figure out how to vote tomorrow, my position has shifted. I think it would make sense, in the course of a human's dialogue with an AI, for the AI to offer to put a set of truthfulness ratings onto a set of statements in response to that dialogue. A human could accept such an offer and save work.
  3. Related to the previous point, the one-way process I've set up isn't good enough. An AI ingests and structures arguments. You have a dialogue with it to refine the arguments. Then you import them into HowTruthful where you assess truthfulness. While I was assessing ballot questions, there were several points where I wanted to go back and use AI assistance to improve the argument tree. Having rated a lot of statements, I didn't want to start over with everything marked debatable. I wanted to start from the partially-rated argument graph. I could do that easily if I had an export button on the main ballot-questions statement. But all I have is an export page for all my private opinions. Manually extracting the right part of that export is clumsy.

That missing export function also makes it clumsy for me to share with you my reasoning for how to vote on the ballot questions. But if anybody asks me to, I'll put it together.