[themodelplumber]

As a systems-minded reader-person:

I like to ask an LLM for 3-5 good ways to know that one really understands the content in question.

Then I ask for examples of each of those, used in a specific setting (code for an app or script I need / project I'm working on, for example).

I also like to pre-read the book based on podcast interviews, YouTube summaries, and so on.

If the book is written from first principles, I will probably find it easier to work through it backwards, as the back of the book is typically where the most functional interfaces to the "world I already know" are demonstrated in such books.

To me this is also a common sign of someone who's a natural systems thinker (since you mentioned the topic): First principles are the wrong end of the learning process.

A natural systems thinker may even hear the phrase "first principles" and immediately start to feel boredom, impatience, and time escaping their grasp. :-)

A systems thinker needs access to working interfaces for systems components first and foremost, not internal components and logic.

This is due to the broad nature of systems work, the interconnectedness of its scope, and so on. Internal logic and single-component foundations focus will effectively block efficiency here.

If it really is more about internal logic of a system's individual component, then this is not systems thinking. Generally here is where you find departure points from systems thinking into more academic-style criticism or analysis. Arguments are definitional in nature and less about work products, economy, or outcomes.

(I also keep a running log and own-structure system if the topic is important to me)

Just some thoughts, good luck.

[qumpis]

On what level of topics do you query LLMs to help you learn? As you become a domain expert, the usefulness of LLMs diminishes, I imagine?

Regarding the learning of learning from first principles vs from 'working interfaces', could this be said as 'learning top to bottom' (high-level ideas first) vs 'bottom to top' (low-level first, e.g. understanding axioms of real numbers before understanding algebra)?

[mtippett]

ChatGPT (gpt-4.0) is crazy omniscient.

It doesn't diminish, the knowledge is like a fractal. You can zoom out, in, etc.

I created a prompt that asks me a set of questions on a topic. It then scores my understanding, gives me deeper insight into the topics, broadens my understanding with some extra information, and then provides a mind-map of related topics, and a mind-map of adjacent topics.

To bootstrap an area of understanding, I ask it for a mind-map of a topic. Like a fractal, you can choose a line item and go deeper.

Prompt 1: Give me a small mind map on the amygdala

Based on that, prompt 2: give me a mind map on the role of the basolateral nuclei of the amygdala in the creation of phobias

[themodelplumber]

Good q's...

I find that domain expertise is really a funny mirage in a lot of ways.

What I want in reading a book is less often book-domain expertise and more often "convert book's contents to my thinking style and existing systems fit." Then I will typically use that result in the domains in which I'm already an expert...that's what I generally find that I want.

For this reason the LLM is helpful in abstraction duties. It doesn't by itself need to be as much of a domain expert, as much as it needs to give me e.g. more fluid interface-mindset access.

On the other hand, if it is lacking even basic quality of internal schema, sure? It's just that this hasn't happened to me yet; maybe that's surprising but it's more likely that this happens based on my own specific questions and theories than with the contents of published books.

So many of the books are functionally general in nature but still foreign in their nomenclature, etc. and I find that this is a good leverage point for an LLM.

> could this be said as

It usually is said that way, in my experience. I personally find it more helpful to talk about interfaces vs. internals. But others may be more used to talking about top-down.

For example with the interfaces metaphor, you get to have more than one "top" which maps very well to systems focus & benefits IMO. The leverage here is very useful in some teaching and learning cases.