I’ve been working on my comprehensible input reader app for Spanish. I’ve recently added a nice review system at the end of each story, that goes over the top words the system thinks you need to review, but shows the definition, synonym and an example sentence all without a English translation. I’ve also improved the onboarding system to feel less challenging and less like a quiz.

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 website is called https://readplusone.com if you’re learning Spanish and interested in checking it out.

Spanish is the current focus, I want to add more grammar features, so stories help target the readers grammar weak points. But after that I am planning to expand to other languages and most likely other Latin based languages as it will be the easiest to expand support to.

Thank you, I’m glad you like it. I actually was never planning to add translation support but I added some after user feedback. But I’ll add multi-word translation onto my roadmap.

That would be great! Also being able to add short multi-word phrases to the repetition

That makes sense, I do need to calibrate and store recorded words for the user in the database after that. Do you think a user would be more off put after taking the time to do a quiz, to then realize they need to create an account?

I’ve been working on my comprehensible input reader for Spanish still. I launched the beta exactly last month and it has been going well.

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.

https://readplusone.com

I've been working on a Spanish language learning tool that helps users learn with comprehensible input. It uses LLMs to generate targeted stories for the users and while the user is extensively reading they select any words they don't understand. Those words then get added to a space repetition deck and are used in future stories when it's time to review the words again.

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.

https://readplusone.com

Very cool! I made something similar a while ago for learning Mandarin Chinese. Unfortunately more basic than your Spanish version: https://dailychinesestories.com.

I miss working on language learning tools. My attempts were all in the ~2024 era of LLMs.

Thanks! And you're website looks pretty cool.

You should try working on language learning tools again. The models now are pretty good especially since you don't always need the frontier model to generate good stories. I would love for this project to get solid traction so I could distill my own models that are better at meeting my story creation requirements.

Appreciate it! I plan to. To be fair, I've made small updates here and there to this one. Just no overhaul/expansion yet.

Best of luck on the beta & release!

I’m working on a language learning tool where it uses LLMs to generate stories at your ideal level. The idea is the user would be provided stories that are 95% comprehensible, with the other 5% being a mix of brand new words or words you are still learning. As you read the story you click on words that you still don’t fully understand. I am only working on Spanish right now, since I want to optimize for each language. It’s been fun designing my databases, coming up with calculation ideas, designing story validation, creating an estimation system of a user’s knowledge for onboarding. I know there is some debate about LLMs in language learning and I don’t think they should be trusted to explain grammar but if you validate it’s output it can be such a great tool to learn at your perfect level.

That sounds really interesting. I have a similar project, albiet pretty small. I want to generate comprehsnible input stories for the user say with 98% known words and 2% unknown words. Instead of rewriting stories though, I thought of having compiled list of books with say a book's top 1000 common but unique words, then you can add it to your desk and have those be generated in stories. That way once you complete the deck, it will be a lot easier to read your target book. I was looking into using numPy for that, not sure if you are using Python but it might be worth looking into.