brandonc7

I was dead set for a while that just reading with 98% knowledge of the words in the story would be enough to learn the new words through context but in reality that’s not always the case. So I have been trying to adapt the system to work better for the user while still staying in the comprehensible input area that I want my project to focus in.

I’ve also been wanting to start work on the mobile apps, but the PWA works well enough and I know it’s better to spend my time on other features/improvements before doing a full native or react-native implementation.

The project combines the idea of graded readers with spaced repetition systems like Anki. You generate stories with LLMs that are tailored to your Spanish level, then click the words you don’t know. As you read more stories, the system brings those words back naturally in future stories so you keep seeing them in context.

That’s how it works on a high level but behinds the scenes, there is a good amount of natural language processing going on, majority with the spaCy package. I’m hoping one day to post a blog about it on here.

It’s been awesome to see it actually being used by people and I have had fun talking with users and implementing feedback. At my current job, I usually don’t get that level of customer interaction so it’s been nice.

I’m hoping to take it out of beta soon and launch a paid tier with higher story generation limits, while keeping a free tier available. The goal is mainly to start covering the cost of running the project and keep improving it.

If you’re learning Spanish and have a A2 level or higher feel free to check it out. And even if you don’t know Spanish feel free to ask me questions about it, I would love to talk more detail about it.

The project has been really fun to work on because of the fun systems I've had to think about. I had to figure out the optimal way to store the user's knowledge of the words. For example you don't need to store the singular and plural of a word in Spanish or even every verb tense, you should probably store the lemma and track those modifiers instead. It's also been a fun challenge to tell the LLM the user's Spanish knowledge without specifically sending every lemma/word the user knows.

I have seen some similar projects out there but a lot of don't seem to focus on creating the perfect story for the user and instead have them choose a CEFR level (A1,B2 etc). Which I think defeats the whole point of using the LLM. With computers we have been able to track a user's knowledge granulary but now we can do the exact same thing but for creating.

I'm really excited to see how far I can take this project. I wanna continue to polish it, but also there is so many details I can continue to add the make the ideal language learning reading app. I just launched the beta last Tuesday, so if you are learning Spanish, I would love if you tried it out and gave feedback.