Maybe I was doing it wrong. The question is: how do you prevent the AI from falling into a corrupt state from which it cannot get out?
Domaindocs is a nice no DB solution and easy thing, but got some issues with it. I create the domaindoc, add manually something inside (list of friends, Name - description), and enable it. Later I ask what I put inside, or who is x, and I got the correct output, but when I try to ask to replace x word by another, he show me what it should be, says is done and completed, but does not edit the actual domaindoc file.
This is easily one of my favorite descriptive details I've ever seen in a README.
What would you think about adding another column that is used for matching that is a superset of the actual memory, basically reusing the fingerprint expansion prompt?