Live data from Hacker News

How to write good prompts: using spaced repetition to create understanding

andymatuschak.org

21–30 of 46 posts

Re: How to write good prompts: using spaced repetition to create understanding

#21
post #18

I find that writing spaced-repetition prompts in the way the article describes to have too small of a return on investment: Reviewing them is quick, but it takes a lot of effort to craft good ones from a text. Good authors take care with their prose and use nuance to get their point across, which is often lost in the translation to a few bullet points. This subtlety is often the meat of the text, and the high-level p…

> it takes a lot of effort to craft good ones

Though this engagement itself aids memorization...

I'm not a fan of spaced repetition, instead preferring to understand material and find connections (associations) integrating it within my existing knowledge. This makes it usable, not just recallable. It's holographic, in that I can also recover it from other things I know, like the shape of the missing jigsaw piece, or a theorem or proof.

However, I've come to realize that the very act of engagement to understand is, in itself, aiding memorization.

Re: How to write good prompts: using spaced repetition to create understanding

#22
post #18

I find that writing spaced-repetition prompts in the way the article describes to have too small of a return on investment: Reviewing them is quick, but it takes a lot of effort to craft good ones from a text. Good authors take care with their prose and use nuance to get their point across, which is often lost in the translation to a few bullet points. This subtlety is often the meat of the text, and the high-level p…

> it takes a lot of effort to craft good ones Though this engagement itself aids memorization... I'm not a fan of spaced repetition, instead preferring to understand material and find connections (associations) integrating it within my existing knowledge. This makes it usable, not just recallable. It's holographic, in that I can also recover it from other things I know, like the shape of the missing jigsaw piece, or…

A key insight for me was when I realized that spaced repetition isn't really about memorization, it's about skill maintenance.

The skill most people use formal spaced-repetition methods for is factual recall, to be sure, but the underlying principles can be applied to any human endeavour. My Anki deck, for example, is designed to exercise reading comprehension. For cooking, I don't try to memorize recipes like the article demonstrates; I do, however, try to revisit and make the dishes in my repertoire semi-regularly to reinforce the operational cues that are impossible to put into words. It's similar for all of my other hobbies: I naturally tend to have a period of intense engagement with them at first that trails off as my confidence builds. I seem to revisit most of them on the same sort of exponential schedule without really trying, as if my subconscious understands when it's time to have a refresher.

Re: How to write good prompts: using spaced repetition to create understanding

#23
post #18

I find that writing spaced-repetition prompts in the way the article describes to have too small of a return on investment: Reviewing them is quick, but it takes a lot of effort to craft good ones from a text. Good authors take care with their prose and use nuance to get their point across, which is often lost in the translation to a few bullet points. This subtlety is often the meat of the text, and the high-level p…

Really interesting how you extract cloze deletions from ebooks! It sounds very similar to what I'm building with Traverse.link, a social spaced repetition app with connected cards. You can import an article (working on ebook support), and it'll turn the paragraphs into cards, to which you can then add cloze deletions and free form prompts.

Re: How to write good prompts: using spaced repetition to create understanding

#24

Is this written by GPT-3?

Exactly my thoughts. The article is all pseudoscientific hogwash.

I skimmed through to understand what it's about or at least to know what a "prompt"/"spaced repetition" is. I still don't know, but I bet it's something very trivial.

Re: How to write good prompts: using spaced repetition to create understanding

#25

Is this written by GPT-3?

Exactly my thoughts. The article is all pseudoscientific hogwash. I skimmed through to understand what it's about or at least to know what a "prompt"/"spaced repetition" is. I still don't know, but I bet it's something very trivial.

I find it peculiar that you can confidently dismiss something as pseudoscientific hogwash while simultaneously admitting that you don’t know what it is.

This might help:

https://www.gwern.net/Spaced-repetition#

Re: How to write good prompts: using spaced repetition to create understanding

#26

Is this written by GPT-3?

Exactly my thoughts. The article is all pseudoscientific hogwash. I skimmed through to understand what it's about or at least to know what a "prompt"/"spaced repetition" is. I still don't know, but I bet it's something very trivial.

Man, those two comments sound uncharitable. In the first paragraph Andy states:

> This guide assumes basic familiarity with spaced repetition systems.

The words "prompt"/"spaced repetition" are basic jargon for such systems.

But to make this comment at least a bit helpful, too: An example of a "prompt" in a spaced repetition system is the front of a flashcard. It's "spaced repetition" because you look at them multiple times, spaced out over time.

Re: How to write good prompts: using spaced repetition to create understanding

#29
post #25

Earlier quoted context omitted.

Exactly my thoughts. The article is all pseudoscientific hogwash. I skimmed through to understand what it's about or at least to know what a "prompt"/"spaced repetition" is. I still don't know, but I bet it's something very trivial.

I find it peculiar that you can confidently dismiss something as pseudoscientific hogwash while simultaneously admitting that you don’t know what it is. This might help: https://www.gwern.net/Spaced-repetition#

Because one can recognize the signs of pseudoscience even without knowing anything about the subject matter. E.g.:

- obscuring language

- missing references and/or imprecise citations

BTW your link does not explain what a prompt is.

Re: How to write good prompts: using spaced repetition to create understanding

#30
post #25

Earlier quoted context omitted.

I find it peculiar that you can confidently dismiss something as pseudoscientific hogwash while simultaneously admitting that you don’t know what it is. This might help: https://www.gwern.net/Spaced-repetition#

Because one can recognize the signs of pseudoscience even without knowing anything about the subject matter. E.g.: - obscuring language - missing references and/or imprecise citations BTW your link does not explain what a prompt is.

A prompt in this context is just the side of the flashcard that prompts you to remember the "other side"/answer. They can be questions, sentences with words missing, or many other things. E.g. for learning a language a prompt could be the English word, prompting you to remember the translation. Gwern calls them "questions" in his article, but "prompt" is more general, given that they're often not phrased as questions.

There are many examples of prompts and answers in the main article, with blue backgrounds, and prompts about the article's content with red backgrounds.

Post reply on HN