Don't build a spaced repetition startup

Post by jamager » Fri, Sep 19, 2025, 12:21 PM UTC

I am working in this space as well. Habit formation / self-learning is a big easy because overwhelming majority of people prefers more structured / guided content. This makes SRS very niche.

The part of seeing "You still need to decide what’s worth remembering" as friction I strongly disagree with.

That is a very important part of the learning process and IMO should not be automated. It is difficult because learning is difficult, but if you kill that you also kill the spirit of self-learning!

And not mentioned in the article, but I think the most important factor is that everyone in the SRS niche knows Anki, and despite Anki faults, everyone has put the effort to learn how to use it, got used to it, found a good-enough workflow, and have zero incentive to move to a more expensive alternative even if it is better.

Post by rsanek » Tue, Sep 23, 2025, 11:41 PM UTC

Great write-up. I especially liked

> I find the common advice of “write your own cards” misplaced: you pay the opportunity cost of not reviewing all the cards you don’t make.

This perspective of cost is a nice way of putting it. The other side to me is that writing your own cards can, but does not necessarily, improve retention on its own. Much of card creation is still mostly manual formatting, copy-pasting, etc.

My own solution to this has been to build an 80-20 version of what was demo'd in the "AI canvas" part of the video. I drop in a source (pdf, epub, etc), and an LLM prompt creates cards. I just use Anki Connect to directly add these cards to my collection.

Would be interested in seeing the Rember system prompt for card creation, and hearing what LLM is being used. I've seen wildly different results from changing my own prompt (and from using different models).

Re: Don't build a spaced repetition startup

Re: Don't build a spaced repetition startup