> 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?
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.
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).
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 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]
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.