Spaced repetition systems have gotten better

I see a lot of discussion about SRS, and I think most can agree they have improved.

What I would like to see covered is a more vague area, but almost more important:

It’s the space in between reading/understanding something and the SRS. There are almost no standalone tools dedicated to creating flashcards easily from existing programs (web browser, PDF readers etc.) into popular SRS (Anki, Mochi etc.). They should work almost as OS additions to make everything feel native and frictionless; I don’t need another standalone tool that does X Y and Z, I just need some sort of pipe into an SRS that is Mac friendly and does the job whilst not being in the way.

If someone knows of such a tool, I would love to hear about it.

Just tried RemNote with their AI-generated cards features and so far looks amazing. They can generate cards from PDFs, webpages and notes.

I've written my own flashcards app (Fresh Cards) and once in a while, users ask if there's a way to import flashcards from things like web pages and PDF files, but to be honest, I still don't know how it would work, so maybe you can help me.

From a user standpoint, would it be an interactive process where you highlight things and then click a button to say "turn this into a flashcard", or would it be an automated tool that would scan the content and come up with a list of questions and answers t hat would test the material for you? What criteria would be used to determine what's worth turning into a question and answer? And how granular should the question be? I've seen demos of things that pick out specific facts, like dates or names, from the text to turn into questions, but that might not be that useful to quiz for some material. It seems like a very open-ended process to me, so it would be hard to get right for everyone's needs.

The macOS services model seems like a good fit for this kind of thing. Services are little bits of context-aware functionality that apps expose to enable integration between apps without active developer involvement. An example, in most Mac apps if you select text, right-click to open the context menu, and open the Services submenu you’ll see a number of services that do something with the highlighted text.

Ideally the SRS app would make services available to facilitate quick creation of new cards, so for example one might highlight some text, right-click, and select Services → New SRS Card… which then opens an in-place lightweight card creator dialog.

I've tried Fresh Cards so thank you for developing that app, and trying to add cool new software into the space.

Great question. Here's one way to do it:

The first is how clunky the process of going from X to flashcard feels to the end user. One way to deal with the fact that we are crossing software border is to add an extra step where highlighting something allows you to go into an "inbox" before any cards are made. It is clear what the user has to do. They read something interesting, and add it to the inbox. When they are ready, they can head over and only then use some sort of automation (either via custom prompt for an AI or otherwise) to make the cards. This gives them another step, or interface, at which they can decide whether or not the thing they highlighted (since highlighting is easy) is actually worth something. It segments the process into clear easy sections: highlighting, deciding which highlights to flashcardify (and therefore keep), and flashcard review.

It definitely is an open-ended process, and I appreciate that apps need to have a strong opinion on how to direct users from start to finish; but I feel this is definitely possible now with cheap and quick AI.

I didn't answer every question but hopefully that helps somewhat.

I hadn't thought of this; thank you for bringing this up. I will actually read into this. I didn't write it in my original comment, but I almost mentioned the OS because I'm coming round to the idea (albeit slowly) that the OS needs to provide some sort of hook into this capability natively for both maximum adoption and also ease of use (for both developer and end user).

Perhaps Shortcuts are now powerful enough to do this as a PoC, providing the SRS has some sort of open API that Shortcuts can take advantage of.

Thank you - I'll give it a try!

I appreciate the detailed answer. That's a really good point about the software boundary and how that adds friction to just creating cards in the first place.

I like the idea of an inbox where you just toss things you think are worth remembering and maybe having a browser plugin or OS shortcut to save highlighted bits of info, but not necessarily creating a flashcard immediately from it. There's definitely some concrete things I can prototype here to try to make that workflow easier. And I can see how taking those tidbits of info and passing them to AI to create flashcards is doable too.

This mostly works with Mochi - you can paste PDFs etc into ChatGPT and the Mochi markdown format is simple, so it can generate flashcards for you (I have the format explained in my system prompt so I don't have to re-explain it every time). This synergizes nicely with the fact that you really want to understand something before you make flashcards from it.

If you pay for Mochi you also get API access, so one could make a ChatGPT wrapper which adds the cards for you. But since I like to review the cards manually before adding I don't mind the copy paste step.

> It’s the space in between reading/understanding something and the SRS. ...If someone knows of such a tool, I would love to hear about it.

I have a slightly different system I'm developing:

Rather than reviewing with flashcards, review with actual content:

1. Tag the content with the words and grammar concepts

2. Estimate the difficulty [1] for you of each word or grammar concept -- the difficulty being essentially the inverse of your familiarity graphs in this article.

3. Choose content to read which balances difficulty and the impact on learning.

Since reviewing something you're about to forget has more impact than learning something new, "spaced repetition" falls naturally.

And instead of spending your review time going through flash cards, you spend your review time reading content in the target language.

[1] If you know the details of the FSRS algorithm, I'm using "difficulty" here differently than they do in their algorithm.

Some examples I'm aware of (mostly in the language learning and especially Japanese learning space)

- subs2srs MPV script: create srs cards from subtitled videos, if you have subtitles tracks for source and target language it will fill them both in (though that sometimes has caveats, different languages may distribute the meaning of a line of dialogue over different subtitle lines)

- asbplayer chrome extension: inject extra subtitle languages into streaming services and create flashcards from them similar to subs2srs

- yomitan: browser dictionary lookup, primarily for bilingual dictionaries for Japanese and Chinese but also has custom dictionary support.

> the OS needs to provide some sort of hook into this capability natively for both maximum adoption and also ease of use (for both developer and end user)

I’m absolutely of this mind, but unfortunately it also depends on developers’ willingness to make use of these hooks, and it’s becoming increasingly uncommon for third party apps to have any integration or automation affordances, especially any specific to any particular platform. It’s become the norm to ship the absolute bare minimum, which is the lowest common denominator “it runs”.

On Mac, you could make a little Shortcut that accepts your text selection or maybe even a screenshot and sends it to AnkiConnect to make a new note. Add this Shortcut to your share sheet and you can create new notes from any app. Later, go over the notes in Anki and add questions or if really lazy send the backsides to an LLM to create those questions.

I was an early user of FreshCards, and it’s a beautiful app, but creating cards was too much work. No share sheet or similar integration.

The easiest thing, which I believe I suggested, was highlight->action to create a new card front, and highlight->action to creat the back or a new front. It needs to work well casually in general, and easy when focused.

I’m sure AI could theoretically help but not sure it’s necessary. Part of the benefits of most cards is creating them yourself.

The INBOX idea would be a great improvement! That plus a reminder to process your INBOX after N time or size.

The hardest part of any system is making it a habit.

> There are almost no standalone tools dedicated to creating flashcards easily from existing programs

I think this is a common misunderstanding. Half the benefit of SRS comes from working out what the flashcards are. You have to circle around a concept, look for similarities, differences, examples, generalisations, properties, etc.

Is it hard work? Yes. Does it help understanding? Massively.

This is also a very difficult skill which, I believe, is why many people fail to appreciate SRS. They try, write bad flashcards, don't see results, and give up.

EDIT: This also leads to another common misunderstanding, that SRS is only good for memorising facts. With proper elaboration (thanks child comment), it can be used to build understanding of complex subjects too.

The technical term is "elaboration" and it is key to long term retention.

I’d say a missing thing is figuring out the order in which cards have to be shown.

Showing schlafen before ausschlafen, or contextually simpler cards before more complex ones.

Optimizing blindly easy medium hard and next time to show a card is probably very far away from efficient learning.

If the process is inspected, most of the forever knowledge that I acquired I heard once and internalized.

I've never used it, but my understanding is that something that does this is considered a "killer feature" of Supermemo. It has a mode that lets you read text (via a PDF viewer) and lets you create flashcards as you read in some kind of semi-automated way. Or something like that. Like I said, I never used it.

No, not PDF, only HTML. There are community companion programs like SuperMemo Assistant, that enhance SM, but it‘s all fiddly.

I paid for two SM versions and went back to Anki. It‘s very idiodyncratic, the user interface is atrocious (in the latest version it finally, finally added thumbs up/down icons for grading the answer —- before that you had to remember whether 1 is good and 5 is bad or vice versa).

SM is fascinating (including task management, sleep cycle tracker etc.), but it‘s held back by its technological choices (only support for Edge or IE, and Edge only in the newest version), and for incremental reading you‘ll be mostly ingesting Wikipedia articles, because PDF isn‘t supported.

Fair point, please see my comment in response to allenu, in this same thread, for a detailed view.

I did not mean to glaze over this aspect, I am aware this is very important. I can not and do not use AI for automating flashcards for this reason alone. But, I think my point still stands, getting information from one disparate app into another adds a lot of friction (saving it somewhere, copy and pasting and yada yada) to something that (I believe) should be as easy as possible. We have 1 click instant payment, but I can't have 1 click get this into some sort of inbox in Anki ready to flashcard-ify?

To be honest, I have a whole frustration with apps and windows that I'm still trying to word, but fundamentally all we are doing when we are "computing" is moving information around. I wish that information was a first class citizen at the OS level that could be leveraged by any app immediately. Utopian view but this stuff ain't gonna think about itself.

No problem - I'm happy to help. I spend way too much time thinking about this type of stuff.

I'm glad this has resonated, good luck with the prototypes. Let me know if you ever want more feedback.

I agree, we need something with a caring UX which encourages habit-forming. I feel like this space is very underexplored, especially considering the 1000s of note-taking adjacent apps made in the last decade.

A great shame, I see your point. I guess it comes down to the developer treating their product as something that could "help people" or something that "pays the bills". Hopefully the former would lead them to caring enough to spend the extra time for these significant QoL improvements.

+1 SM is really interesting. Supermemo.guru (URL) is a fascinating resource written by a fascinating person (the creator of Supermemo), but the software is so unusable that it immediately shoots itself in the foot (or head). I don't think anyone should ever use it, but people should take away from it interesting concepts that they can use when writing new software.

Thank you - I hadn't considered this.

Yes, I do something like this now. It definitely does do the job. I just wonder if there could be something more, something smoother perhaps, and the API access could do the trick.

It's tricky I think, I think it comes down to specialized tools for different systems. I'm building a tool for Japanese in this direction. But of course it doesn't generalize to everything since the content and context extraction is very objective dependent.

I agree, it is tricky. But I believe it is possible, see my response in this thread to the user allenu as a middle ground.

Thanks for the feedback! I'm currently working on a big rewrite of the app, so it's good to know I should work on reducing the friction of creating cards, such as with the share sheet or some other integration.

Like I said in the other comment, I'm going to play around with some ideas regarding an inbox. I think that on its own would help a ton for just recording things to be converted to flashcards later. There's probably a good in-app UI that can be made to go through the inbox and easily convert the notes created into the front and back sides as well.

I solve this problem with a system prompt in my LLMs[1].

ChatGPT is the main spot where I'm going to be trying to understand a new concept, so after groking it I'll ask it to make flashcards which I can then just copy and paste into Mochi.

An improvement would be some sort of MCP integration between the LLM and Mochi so it can just add the card directly. I'm sure we'll get there soon.

1. https://gist.github.com/christiangenco/db4b61c315b93fc2a404a...

That's usually done by writing and elaborating notes. I think it's not clear to most people how flash cards improve this. The original idea of flash cards is rote memorization of facts that need fast (automatic) retrieval.

AI definitely helps here (and it's the direction I'm going), although to start exploring the space in a way that makes sense to me (and because it's a problem I have), I've reduced the space into these steps:

  * I wanna be able to watch X in Y language
  * I know these words
  * Help me

This is how anki already works on Android, using a custom intent.

Okay on first try, this seems promising, I'll try the pro sub tomorrow properly and take it for a proper spin, but:

- I read a lot of PDFs. I can click a sentence and have it suggest cards, or fill my own.

That's already a great start on the "space in between".

Not sure I understood the gist, but let me try summarise what you do generally (i.e. not just for language learning).

- Instead of flashcards, you read content/write notes. - You tag said content in some way which allows you to understand how difficult it is. - When in "review" mode, you essentially choose what to reread based on the difficulty you are feeling has the most impact right now.

I built a native flashcard app for mac that includes spaced repetition. You can close the main window, so it is not in the way and just select add flashcard from the top right menu bar in whichever application you are in

https://apps.apple.com/us/app/flashcard-max/id1430950704

> They try, write bad flashcards, don't see results, and give up.

But if that's the case, then wouldn't a program that takes a long text (like a book) and creates GOOD flashcards, be way superior over someone making their own bad flashcards?

The quality of a card isn't absolute, it's personalized to the learner. There are ways to make an almost universally bad card (e.g. putting way too much information or a misleading image), but a really "good" card comes from the learner engaging with the material first before making the card.

The program doesn't know what's in the learner's head and what associations the learner will make. That's the benefit of making your own card.

Or a person could have the program either critique their flashcards as they write them, or suggest new sorts of flashcards to create without doing the work for them by automatically generating them.

Now I wanted it for myself and just made it. So at least I can confirm this works.

Only difference is I don´t actually use the sharesheet much so I do it with clipboard content: Step 1. Take screenshot or copy text. Step 2. Make a request to AnkiConnect and have it create a new card with clipboard in Anki.

Works flawlessly on Mac/Desktop but if you want to do it from mobile devices, you have to muck around with network permissions. Too much for this evening but this alone opens up possibilities.

Thanks for the stimulating question! :)

You can add my https://github.com/hiAndrewQuinn/audio2anki script to the space, in a similar position to subs2srs.

The big thing my script does differently is run Whisper locally to actually generate the subtitles from the video themselves. Most videos out in the real world don't come with convenient little SRT files bundled with them.

It doesn't yet shell out anywhere to automatically provide a translation, but that's more because I was already past that stage for most of its output reading-wise. It's explicitly tuned to make listening practice SRSable.

(I originally built this for learning Finnish. For the other 2 people here on that journey, https://finbug.xyz/ is where I've collected the other software I've built over the years for this.)

I can see that helping a beginner to get a lay of the land, but I see that as no more than training wheels.

I created bad flashcards for a long time. In the end, I just figured, constantly editing cards when I noticed issues was the best way to learn how to use flashcards properly.

This is what we've built RemNote for! You can add your sources (PDFs, websites, YouTube, etc.) and create cards directly from them. Either with AI (click on a sentence => get an AI card), or by highlighting a sentence and writing your own card.

It's not at the OS level, but I think a focused standalone all-in-one experience is actually better. We've explored a chrome extension here that does something similar to what you suggest, but it somehow hasn't proven useful in practice. I always keep coming back to just doing everything directly in the tool (upload PDF, take notes, make cards), as it helps me focus deeply on what I'm learning.

Agree - making cards yourself is like programming yourself for how you want to understand and remember an idea.

I have just tried this afternoon to create with Gemini 2.5 Pro Anki cards to study for my exams. I've been doing it raw: I just paste the whole material (like 100k worth of tokens) into aistudio and generate the flashcards in txt format.

For now it's going great, and I think that the cards are good enough as they are (there might be a couple here and there that I would remove or edit, but they don't get in the way of learning).

Love RemNote -- ability to take notes and create SRS cards within the notes is so sick

Does RemNote use the algorithm described in the link or something else?

Yep, you can either use FSRS (the one described in the link), or Anki-SM2.

Is there any prompt tips you have learned on that path, that you could share? or the obvious request has been useful already without too much fiddling?

I was thinking to use some study material to test drive Google NotebookLM for this use case.

You might be right. I remember when I used SRS seriously for language learning, I got far more out of the cards I created painstakingly than the pre-built ones that I pulled off the shelf. That is - I still remember most if not all of the custom cards verbatim.

I haven't tried many variations yet because a basic prompt seems to work well, thought it is important to remind Gemini of not using ";" inside the text of the cards if you use it as a separator. I imagine that with better prompts you could get it to generate very nice flash cards, but I'm in a little tight schedule, so I can't play around it for too long.

Another nicer option I think would be using the structured output of the API to generate the cards in JSON format, and the parse it to the Anki format with a script, but I think this approach is fine for me.

The prompt I'm using is this

---

Using the information in these PDFs, make some Anki cards to study for an exam.

The format for Anki cards is

```

front1;back1

front2;back2

front3;back3

```

Remember that you can't use ";" inside a field because it is used to separate the front and back of a card.

If the back of a card is a list of elements, prefer to use "<br>" to specify a newline.

I have anki on Android and I never see options to use it from another app. Do I need to set something up?

This reminds me of the share feature on mobile phones which gets plenty of use by developers. Seems quite possible to make something like this on a standard OS

I do this with my kids' "exam review" materials. I'll take a photo of the pages marked "study this for test" and send to Gemini and say "make a test out of this" and it'll create an exam with questions, answers, multiple choice, true/false, fill in the blank, etc.

It's really impressive. So I just tried it to do what you were asking:

> Give me the first three paragraphs of Genji Monogatari in Japanese (I've only done this for an initial seed text; you'd probably instead use your own source text)

Here are the first three paragraphs of Genji Monogatari (源氏物語) in Japanese:

いづれの御時にか、[snip]

> Create spaced learning repetition of those three paragraphs using cloze detection for any word that is not in the top 5000 most common Japanese words

Okay, I can help you create a spaced repetition exercise for those three paragraphs from Genji Monogatari. This will use cloze deletion (fill-in-the-blanks) for words that are generally less common in modern Japanese or are characteristic of classical Japanese. Since I don't have a real-time tool to check against a specific "top 5000 words" list, I'll select words based on common knowledge of Japanese vocabulary and classical forms that would typically be targeted for study.

Please note that the third paragraph you provided contained "тревоしき", which appears to be a transcription error. [This is true. Gemini's first three paras of this novel did contain this transcription error.] I will substitute it with "あさましき" (asamashiki), meaning "shocking" or "deplorable," which fits the context of referencing Yang Guifei and potential societal disruption. If you believe another word was intended, let me know!

What I received was a canvas I can export to Docs, and it begins with:

Genji Monogatari - Spaced Repetition Cloze Exercise This exercise is designed to help you learn and recall less common vocabulary and classical expressions from the beginning of Genji Monogatari.

Paragraph 1 - Cloze Test いづれの ______ にか、______ 、______ あまた ______ たまひけるなかに、いと ______ き際にはあらぬが、すぐれて ______ たまふあり ______ 。はじめより我はと ______ たまへる ______ 、______ ものに ______ そねみたまふ。同じほど、それより ______ の更衣たちは、ましてやすからず。

Paragraph 1 - Answer Key いづれの 御時（おんとき）にか、女御（にょうご）、更衣（こうい）あまた さぶらひたまひけるなかに、いと やむごとなき（やんごとなき）際にはあらぬが、すぐれて 時めき（ときめき）たまふありけり。はじめより我はと 思ひあがり（おもいあがり）たまへる 御方々（おんかたがた）、めざましきものに おとしめ そねみたまふ。同じほど、それより 下﨟（げろう）の更衣たちは、ましてやすからず。

Paragraph 1 - Vocabulary 御時 (おんとき): reign, era (honorific) 女御 (にょうご): Imperial consort of high rank 更衣 (こうい): Imperial consort of lower rank than Nyōgo あまた (amata): many, much (classical) さぶらひ (saburahi): (archaic form of 侍う - saburau) to serve, to be in attendance (humble) やむごとなき (yamugotonaki/yangotonaki): exalted, of very high rank, distinguished (classical)

[it continues the same way with para 2, 3]

Isn't there a Netflix and browser tool where it'll grab subtitles for shows you're watching and create flashcards or something?

Anki has AnkiConnect which is exactly this, I think

https://ankiweb.net/shared/info/2055492159

IIRC Yomichan (been a long time since I needed tools like that) is a Chrome extension that lets you mouseover words and it'll show you the meaning. I think you can invoke something in Chrome that will trigger the Anki Connect API and send the info to Anki to create a card.

I've never bothered with this, but I think that's what you're looking for.

I've fiddled with a bunch of stuff - macros, standalone programs etc - before finally settling on copy and paste. I just copy and paste a page of PDF into Anki then cloze single words (~6-15 words a page). I've worked through several textbooks this way.

Supermemo is neat but it seems too dependent on the whims of one guy. Same reason I'm hesitant to use LingQ to learn languages.

Yomitan (https://yomitan.wiki/) does this

If you're speaking in the context of language learning, there definitely are some great tools for "mining" audio cards from YT/Netflix and also for getting text from the subtitle tracks. Some are open source, free and easy once you get used to working with them (much like Anki itself). They're not frictionless for first-time users, though. Others are paid and a bit more newbie-friendly.