LLM question --> flashcards is exactly the workflow I want. I ask ChatGPT to do a lot of breakdowns of the grammar and the furigana and the words, being able to consolidate that with spaced reptition flash cards just makes a ton of sense. I don't know how hard it is to make this product really high quality, but happy to pre-pay you $10 for example no strings attached (I'm moved to Japan since 6 months ago)
Email is just an odd case today since I was refunding an item. I usually want to focus on phrases everywhere, my yoga/pilates class, baseball team, sometimes TV, sometimes what I hear on a podcast, sometimes on a magazine, and get a detailed breakdown. It's not usually in formal, nor long.
I personally like both flash card directions because it allows me to practice how to write kanji for example instead of just recognizing, or in the context of phrases, it helps me practice active recalling rather than just passive recognition.
I tried so many apps, and was debating whether to build it myself. But it's impossible for me to build - no time and no creative juice left from my main job.
I'm wondering if that would require a different UI or if... Say it just broke up the email for you into separate sentences and input them separately. Then you could click through the sentences one at a time in the existing chat carousel, would that work?
Reversing the flashcards wouldn't be much work, but I've heard that's less useful for learning, since for the English text there's be many ways to say it in Japanese. Happy to add features people will use though.
I tried the app but on the first few attempts it gave an error 404 in console.
The example long paragraph I put in from an email gave me only 4 flashcards, two of them was on Arigatou, when I wanted to focus on the other words: ショップからの回答: [Re] 947912984 につきまして ご連絡ありがとうございます。 ご返送のお手配、誠にありがとうございます。 ご返送品が到着いたしましたら、再度ご連絡致します。 この度は、お手数、ご迷惑をお掛け致しまして誠に申し訳ございません。 恐れ入りますが、よろしくお願いいたします。
Also I couldn't figure out the UI initially, it took me like 10 seconds to think to try the "chat" feature to input into the LLM.