Live data from Hacker News

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

andymatuschak.org

31–40 of 46 posts

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

#31
post #5

What the hell is a prompt? I read a couple pages of the friendly article, waiting and waiting for the missing vocab word to be filled in. I reluctantly opened the link that was an introduction to spaced repetition. I opened the Wikipedia article for spaced repetition. I searched on DuckDuckGo for "Anki prompt" and "Anki what is a prompt" I opened the Wikipedia article for Anki. What the hell is a prompt? Is it the qu…

From the context, it's probably questions. Creating and generating good questions and answers is a skill. Too vague, you don't know if your answer is incorrect or not. If your answer require too much, you're never going to get the answer right, and so forth.

"Questions" is too specific, as prompts are often not actually phrased as questions. E.g. cloze deletions, where you fill in a missing word, or vocabulary for language learning, where the prompt is a word and the answer is the translation.

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

#32
If you are using spaced repetition, or thinking about using spaced repetition with these kind of hand-crafted notes, you might be interested in Mochi[0], which uses markdown note-cards and kind of mixes the Zettelkasten concept and spaced repetition into one app.

[0] https://mochi.cards/

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

#33

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.

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 multipl…

So it is something rather trivial indeed.

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

#34

Earlier quoted context omitted.

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 multipl…

So it is something rather trivial indeed.

Your persistent desire to expose your ignorance and belligerence to us all on this subject is quite fascinating. Spaced repetition as a mnemonic tool and pedagogical technique has decades of scientific research behind it and a simple search on Citeseer leads me to more than a thousand citations. It is neither trivial or pseudo-scientific.

Maybe it is time to stop digging.

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

#35
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.

It doesn't explain what "spaced repetition", "memory", "understanding", or "experiments" are either. It is written for people who already use spaced repetition, and aims to help them improve one aspect: writing prompts. It is not intended as an elementary introduction to spaced repetition, and so it doesn't bother to explain basic concepts.

Your objection is a little like complaining that a computer science textbook aimed at post-grads doesn't bother to explain what a variable is. Some background knowledge is assumed.

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

#36

What people are using Spaced repetition for? Just curious on what people have been studying

I use Traverse.link, a spaced repetition app I'm building, for studying Chinese characters as well as any article or book I'm reading.

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

#37
From the article: "Unfortunately, most spaced repetition interfaces treat each prompt as a sovereign unit, which makes this kind of high-level revision difficult." This is why I've built Traverse (https://traverse.link/), a spaced repetition app with hierarchical and interlinked markdown flashcards, so you study connected knowledge rather than bare facts

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

#38
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…

(author of parent article here)

This is very interesting! Can you say more about the task you perform when you see these prompts? How do you decide how to "grade" your response? Presumably it's not just whether or not you can remember the deleted word(s)?

Also: are you blanking out individual words? Phrases? Sentences? An example would be interesting if you're willing to share!

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

#39
post #32

If you are using spaced repetition, or thinking about using spaced repetition with these kind of hand-crafted notes, you might be interested in Mochi[0], which uses markdown note-cards and kind of mixes the Zettelkasten concept and spaced repetition into one app. [0] https://mochi.cards/

What is the advantage of a proprietary SaaS SRS webapp as opposed to open source Anki? (note that Anki has support for, for example, LaTex, which makes collections in topics such as math highly useful).

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

#40
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…

(author of parent article here) This is very interesting! Can you say more about the task you perform when you see these prompts? How do you decide how to "grade" your response? Presumably it's not just whether or not you can remember the deleted word(s)? Also: are you blanking out individual words? Phrases? Sentences? An example would be interesting if you're willing to share!

Edit: Though my examples below are all fiction, that's half or less of my current reading list. I also have philosophy, research papers, long-form academic books, popular science books, and the like.

-----

For reference, here's the next new card for one of the books I'm reading:

  Bleak House
  Charles Dickens
  CHAPTER III
  ---------------------------------------------------------------------
  coach gave me a terrible start.
  
  It said, "What the de-vil are you crying for?"
  
  I was so frightened that I lost my voice and could only answer in a
  whisper, "Me, sir?" For of course I knew it must have been the
  gentleman in the quantity of wrappings, though he was still looking
  out of his window.
  
  "Yes, you," he said, turning round.
  
  "I didn't know I was crying, sir," I faltered.
  
  "But you are!" said the gentleman. "Look here!" He came quite
  opposite to me from the other corner of the coach, brushed one of his
  [...] furry cuffs across my eyes (but without hurting me), and showed
  me that it was wet.
  
  "There! Now you know you are," he said. "Don't you?"
  
  "Yes, sir," I said.
  
  "And what are you crying for?" said the gentleman, "Don't you want to
  go there?"
(The prior cards include the text up to and including the line starting "But you are!")

My response, having never seen the passage before, was "coat's"; the correct word is "large". The substitution doesn't meaningfully alter the passage: The only thing we know about the gentleman at this point is that he's a stranger whom Esther has just met in the coach, wearing a large coat (cloak?). This is the first time he speaks in the book.

I selected "again" because this is a new card; if this had been a review, I might have deemed it acceptable. The bar for similarity varies depending on the book the passage came from, my mood on any particular day, and how much I care about the contents of the passage. The Rime of the Ancient Mariner, being poetry, doesn't get any latitude: I must remember the word exactly. Some of the tedious battle descriptions in Le Morte d'Arthur get a pass no matter how badly they go wrong.

If a card is causing me trouble, there are a few corrective actions I can take: In some instances I'll edit the card to blank out a more meaningful word than the one randomly selected, which is an easier and more engaging review task. If I can't figure out the blanked word from context, I'll look it up in a dictionary; this happens most often with my second-language texts. And in extreme cases, I have enough coverage of each book that permanently dropping card or two won't cause problems.

The idea for this came from the paper[1] that introduced the concept of Cloze deletions. They were originally envisioned as a readability score. Instead of calculating statistics about the words used, like traditional methods, Taylor proposed to blank out every Nth word and measure how many could be guessed correctly by a reader. Readability and comprehension are two sides of the same coin. They both rely on observing the relationship between text and reader. If used to evaluate the text, this is called readability; if to evaluate the reader, comprehension.

[1] https://www.gwern.net/docs/psychology/writing/1953-taylor.pd...

Post reply on HN