jonathanb88

I'm planning to test German, which also has big differences in language structure.

I expect the app still works well for reinforcing vocabulary, but less well for demonstrating grammar.

You can upload an ePub file within the app.

I'll actually expand on this, because I think it gets at an interesting point, and at a fundamental 'bet' I'm making.

The approach I use should work if there are sufficient 'scaleable' ways to improve accuracy and choose the right phrases. Language analysis, NLP, LLMs etc all help here, and there are many methods I can still use and will add over time. I'm very much at a proof of concept stage right now!

This approach won't work if accuracy improvements quickly reach diminishing returns and an explosion of rules and/or human proofing to handle edge cases are required.

I'm hoping for the former!

It's not primarily rules based as that would be impossible to scale. Where rules are helpful is to provide principles for when a longer or shorter phrase is chosen.

Optimising the tradeoff between more frequent repetition of vocabulary versus better quality grammar examples is where a lot of the work is.

Not currently, but it's definitely something I want to add soon.

I'll look to make it available in more regions soon. I just need to check the copyright limitations for the eBooks made available in the app.

Thanks for the feedback.

This is something that will improve over time - as it gets better at identifying longer phrases I can implement rules so it won't omit a neighbouring noun if the phrase contains a verb.

Something I'd love to look at longer-term. I think an overlay onto the real world that slowly immersed you in a new language would be a really powerful way to learn.

Many thanks for all of the positive feedback today, lots of good ideas for me to get working on; what a great community!

Side-note: A few eBooks are causing errors on the backend that don't appear to be DRM-related. I will prioritise getting this fixed.

I'll take a look. I think there were a couple of features that required 17.0+, but I may be able to solve with an earlier version.

Thanks, I'll take a look!

Thanks!

Thanks for the feedback!

Whilst there are some, often amusing, quirks with the LLM based explanations, I agree that the utility of the app is much higher with them.

Because I'm making public domain books available within the app (from Project Gutenburg), I have to limit the territories it is launched in, as some countries may have copyright limitations.

I will expand the app into more countries once I'm happy none of the books have copyright restrictions there. Feel free to message me with the country you reside in and I'll take a look soon.

Thanks for the feedback, very helpful!

I'll look to fix the first tomorrow, and add the rest to my list.

Definitely an idea on the roadmap. I know most people do most of their reading in a browser and not eBooks.

I'll see how easy it is. I get palpitations thinking about developing on another new platform. Java and Swift were a challenge enough to learn!

Some apps rely upon ongoing LLM API calls for their core functionality. Some require a lot of human editorial work up front. i.e. either high variable cost or high fixed cost economics.

This app lies in a sweet spot where no ongoing API calls are required, everything is pre-calculated (at moderate expense!), but LLMs can scale some of the more 'human' work like explaining translations or checking accuracy. Albeit with the quirks and inconsistencies inherent with the current generation of models.

Thanks for the feedback!

1. I would love to get it to work all the way from a few translations in the target language to a full translation, with a sliding scale in between. 2. It's not connected to the book content. One idea I have is an optional quiz at the end of a session to reinforce new vocabulary/grammar seen. 3. I'll see if I can remove the animation when using the page ahead/back buttons on Android.

Thanks for the feedback! I'll look at adding those.

The app doesn't do anything to remove DRM, so it'll only work with DRM-free files.

I agree - the dream would be to bridge from beginner level vocabulary all the way to a full translation in the target language.

The limitation now is getting consistently high accuracy for whole sentences - but something I'll keep working on as the underlying technologies improve.

English eBooks, with French, Italian and Spanish as the target languages to learn. I will also start looking at integrating German.

Thanks for the feedback! Admittedly the practice feature needs a bit more work. Helpful to know the issues you are experiencing.

It gets automatically deleted after 24 hours.

A few people have raised this. I'll take a look. Unfortunately the App isn't available in all locations.

Thank you!

Thanks! At some point I may add it, but the difference in grammatical structure might limit how well it works. I'll try to start testing it soon.

I think it is SwiftData that meant I had to limit to iOS 17. I will double check because it might be a limitation I can solve easily enough.

Long term audio is something I'd look at, either audio books or podcasts. AR is another long term ambition.

Right now I see this as an MVP to get feedback and see if there is interest. I have no plans to charge for any of the current features.