Mm-hmm.

Like the commentary that I give at different points in the process.

And I'll use this to generate a rubric, and then I'll have it apply the rubric to drafts, and then I'll like do a back and forth with how it applies the rubric and use that to like update the rubric further and see like can this produce something that is capable of giving like good feedback but also like asterisk-y feedback.

And I was doing this process yesterday with Fable, uh, the, the new, um, Claude model to see if it was an improvement over Opus 4.6. And at one point it said to me, 'cause we were like going through a different set of examples, "I notice I am making a lot of updates on every individual case here, and like because of like the nature of the entity that I am, I am inclined to over update on individual like case studies instead of drawing the appropriate broad spectrum conclusions." I'm like, "Yes.

Yes, you are.

And that is what you do and that is the thing that I'm trying to overcome here."

Uh, and, uh, defined in the document multiple times, in case you don't know what a PAC is, it's when, uh, this guy is, uh, attempting to do fundraising and get people to rallies, et cetera, et cetera.

And I want to, stepping back, how do you, like, what do you do with a story where, like, frankly, you know that a lot of people who are reading this are not going to make that distinction, and a lot of people who are reading this are going to use what you have...