How I use AI
Planted 02026-05-05
Personal Field Report
Effectively all of my sessions, regardless of what I am working on, start with this prompt:
Read <source(s)>, and think about <thing to do or evaluate>
My thoughts for better AI outputs goes something like, “How can I give the model better information to reason about what effective
I’ll often use URLs as sources but I‘ve curated a selective source directory built around three kinds of files: Map, Principle, and Index files. Each file is prefixed as such map_, principle_, index_.
Map files are generated from this keyword map prompt that generates a map of literature keywords. This has been an incredible prompt for self-learning. I think of it as step zero in creating the table of contents for a custom made textbook for whatever I’m directing towards at the moment. I tend to make these prompt end in phrases like this:
The field of study I am concentrating on is: Effective <Goal>
Being somewhat situationally specific tends to yield better results for re-using the outputs, so as not to include irrelevant information. But being generic can also yield good results. A few generic examples: Effective Software Testing, Effective Sensemaking
Principle files are a distilled summary of one source, or a small cluster of sources, around a more specific topic. This can be a single map file, or maybe a collection of URLs of articles that talk about a topic or summarize a book. A couple examples: Principles of Software Design (distilled from John Ousterhout’s A Philosophy of Software Design), Principles of Effective Sensemaking (distilled from A Data-Frame Theory of Sensemaking.
Index files are curated lists of relevant Principle files for a broader practical domain. When I’m dealing with a specific task, I’ll point an agent at the relevant Index file so it has a structured set of principles to reason from.
See also:
Media carries with it a credibility that is totally undeserved. You have all experienced this, in what I call the Murray Gell-Mann Amnesia effect. (I call it by this name because I once discussed it with Murray Gell-Mann, and by dropping a famous name I imply greater importance to myself, and to the effect, than it would otherwise have.)
Briefly stated, the Gell-Mann Amnesia effect works as follows. You open the newspaper to an article on some subject you know well. In Murray’s case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward-reversing cause and effect. I call these the “wet streets cause rain” stories. Paper’s full of them.
In any case, you read with exasperation or amusement the multiple errors in a story-and then turn the page to national or international affairs, and read with renewed interest as if the rest of the newspaper was somehow more accurate about far-off Palestine than it was about the story you just read. You turn the page, and forget what you know.
That is the Gell-Mann Amnesia effect. I’d point out it does not operate in other arenas of life. In ordinary life, if somebody consistently exaggerates or lies to you, you soon discount everything they say. In court, there is the legal doctrine of falsus in uno, falsus in omnibus, which means untruthful in one part, untruthful in all.
But when it comes to the media, we believe against evidence that it is probably worth our time to read other parts of the paper. When, in fact, it almost certainly isn’t. The only possible explanation for our behavior is amnesia.
