In your first point, do you mean something along the lines of: given a card, create some sensible cloze deletions? This seems very doable to me. Duolingo seems harder…
I have also come to realize that the feedback is mostly relevant when the questions have some complexity and require longer answers. This seems to be in conflict with the spirit of this post and maybe SR in general. The question-answer-feedback loop does seem pretty powerful though, but I am not certain how to get the most out of it.
And I will have a look at Logseq for some UI inspiration :)
I have been working on an Anki clone that uses LLMs to provide feedback for users during studying and assist in card creation. When you submit an answer the LLM is prompted to: rate the answer, clarify any misconceptions and provide a tip for memorization. In card creation you can upload a pdf or image and the LLM will then generate some cards that you can add to your decks. I will definitely use your ideas in the card generation prompt!
Does this seem like a tool that could be useful to people?
We often operate at some level of abstraction where we understand the thing well enough to solve the problem, without a complete mathematical model (which is actually almost never what we have). You don’t need germ theory to recognise that increased exposure leads to increased decay (canning), or thermodynamics to see that steam applies force. And in some cases cultural evolution just gifts you aspirin and fermentation. What increased understanding really buys you is the ability to one-shot a solution, rather than stumbling onto it by trial and error. If you don’t understand germ theory, you might not think of boiling the can on your first try. Which seems quite relevant for aligning ASI.