Anki helps.
Ask HN: How do you synthesize books that you read?
21–30 of 62 posts
Re: Ask HN: How do you synthesize books that you read?
#22As 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 wi…
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)?
Re: Ask HN: How do you synthesize books that you read?
#23When I used to be an overintellectualizing, overacademizing nerd, I would use complex and regimented notetaking and review systems. The whole gamut from trendy notetaking wiki-type apps to flashcard spaced-repetition apps like anki.
These things made me feel like I was learning. Flashcards and notetaking itself were fun games. I felt like I'd stumbled onto this hyper-optimized efficient way to learn whatever I wanted.
That feeling was misplaced.
I threw away all that garbage and just started diving into things after reading/observing the bare minimum to get the wheels rolling. Read a little, act a lot. The acting is the most important part. You want to learn some thing? Just do that thing, repeatedly.
It's inefficient, failure-laden, and it's the best way to truly learn something.
This applies to abstract things too, like math and language. Don't bother making flashcards for theorems, syntax, or word definitions. You gotta do the work. For math, just do a million exercises. For language, read, write, listen, speak. You can flashcard word definitions and atomic little rules all day, and you'll feel like you're making progress, that's how Duolingo reels in so many people. It's an easy way to feel like you're accomplishing, but it's a facade. Gotta just do the work.
Re: Ask HN: How do you synthesize books that you read?
#24Bit of a shameless plug but I've been thinking about this for a while and I recently built a free/open-source tool called Emdash [1] to tackle the problem. I’m a heavy ebook highlighter, but I found if I didn’t have a compelling way to review those highlights they fell out of my understanding.
My tool uses on-device semantic embedding which allows you to peruse your collection and see related passages from other books which I find really helps in comprehension when you view a related idea in the words of another author. You can also search for semantic concepts directly to see nearby ideas from various authors, which is nice for when you’re in a mood for exploring a particular space via raw concepts.
The demo mode also previews a passage rephrasing feature, which can give you a simplified or metaphorical explanation, which I’ve found really valuable in grokking dense excerpts. This part is powered by LLMs (off-device) but will be opt-in later. I’m trying to gauge interest for it, so there’s a form to sign up for a waitlist if you’d like.
Would love to hear if anyone else uses this tool and what they’d like to see in it. Source code is available too [2].
Re: Ask HN: How do you synthesize books that you read?
#25I listen to a lot of non-fiction audiobooks. Over time, I've realized it's pretty much pointless to try to "lock-in" knowledge. There's simply too much information and generally a lot of noise, relative to the real-world problems I'm solving. I now read books with a few intentions: * Don't read for facts. Read for patterns and mindsets. * Spend enough time in the book to absorb a mindset from it. I don't need all 8.5…
This is the way. Let the book flow through you and change how you think. Embed that stuff deep in your neural network, if you will.
You can always look up facts later if you need them. What matters is getting the vibes and an intuitive feel for the material.
Directional understanding is what I am for. Details, that’s what search is for.
I also like to read in audio, then get a paperback copy if I think later I’ll need to reference details.
Synthesizing the core thesis into a blog/article in my own words helps a lot too. But really good books ooze through all future thoughts and writing anyway.
edit: explaining the ideas to a friend also does wonders. “Hey I read this book about …” works great
Re: Ask HN: How do you synthesize books that you read?
#26I like to highlight in the books. These highlights are words that make me think or resonate with me.
After each chapter, I'll go into a Notion Doc and type out these highlights. Then following the highlights I'll write my thoughts or summarize the highlights in own words.
Sometimes these thoughts turn into full-blown essays. Sometimes these thoughts are nothing.
But I still get the reps in.
After the book is done, I publish some highlights and the thoughts to my personal website.
Re: Ask HN: How do you synthesize books that you read?
#27I have a method that works really well. I only read books on kindle, and i use kindle highlights. After I finish a book, I usually wait about 1 month or so, then I download the kindle highlights and turn them in to Anki flash cards and review them every day. The type of cards i make are 1. vocab i didnt know 2. interesting paragraphs 3. other examples using cloze SMS works, and this method definitely works, but it's…
My approach is similar!
However, my cards are more made for spaced reading than for spaced repetition studying. As such, each card just corresponds to a highlight.
(Also replace Kindle with Google play books)
Re: Ask HN: How do you synthesize books that you read?
#28When I used to be an overintellectualizing, overacademizing nerd, I would use complex and regimented notetaking and review systems. The whole gamut from trendy notetaking wiki-type apps to flashcard spaced-repetition apps like anki. These things made me feel like I was learning. Flashcards and notetaking itself were fun games. I felt like I'd stumbled onto this hyper-optimized efficient way to learn whatever I wanted…
> "Read a little, act a lot. The acting is the most important part. You want to learn some thing? Just do that thing"
Took me a long time to learn this but also came to the same conclusion.
Re: Ask HN: How do you synthesize books that you read?
#29When I used to be an overintellectualizing, overacademizing nerd, I would use complex and regimented notetaking and review systems. The whole gamut from trendy notetaking wiki-type apps to flashcard spaced-repetition apps like anki. These things made me feel like I was learning. Flashcards and notetaking itself were fun games. I felt like I'd stumbled onto this hyper-optimized efficient way to learn whatever I wanted…
I agree with basically everything you are saying, except I think a sprinkle of rote memorization can go a long way in some domains. Whenever I read a math book, memorizing definitions and some key theorems helps me apply them in problems. With programming, however, I tend to do zero rote memorization.
Re: Ask HN: How do you synthesize books that you read?
#30As 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 wi…
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)?
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.