Earlier quoted context omitted.
Happy to do so. Probably not something a lot of folks here would find interesting, but I'm easy to contact, from my Web sites. People here, often do that. Basically, my needs are different from others. I'm not working on the next NORAD upgrade, much of my work is open, and the more ChatGPT knows about me, and the app I'm designing, the better. One reason I chose it, was because of this "memory." TL;DR: I feed it just…
When using LLM's to help write things like tutorials, how do you reduce the verbosity firehose? Even though I use MD/skills and other methods, I have remind models that they are not paid by the word multiple times a day.
For example, I have made a tutorial, which is meant to be a "quick reference," from within the app (Use Safari to view the page), but I am also developing a "walkthrough," to show possible funders (we're an NPO). The walkthrough is a higher-level vocabulary than the tutorial. The LLM deals with stuff like making sure to keep the glossary consistent, etc., but I like to have the final say on the output.
I'm pretty sure that I can force the LLM to use certain levels of vocabulary, through the .md file that describes the default setup, but choose not to do it.
I am still in that "trust, but verify" stage of my relationship with LLMs.