Then again, it's also good to not lie to your users.

Your courses are AI-generated and not curated by experts.

I tried the French beginner course, using German as my base language. The very first items were:

1. Hallo (hello) > Bonjour (I think salut would be better)

2. Guten Morgen (good morning) > Bonjour

Then it asked me what Bonjour means, and selecting Guten Morgen is wrong, correcting me to Hallo. Then it asked me what Bonjour means again, this time Guten Morgen is correct.

So yeah, good initiative, but please just tell me what it is and don't lie.

You say you learned Turkish with lairner. What level of fluency did you achieve? Are you able to take in native content with full comprehension?

Edit: I'm not trying to be argumentative, I see a lot of people come on Show HN with these fantastic projects but are poorly marketed. You seem to have some differentiator but I'm not seeing it in action. I wish you the best success with this, and I can assure you, if it's as good as you say I will be your biggest customer and fan.

Honest question, how? If this is a side project so you're presumably the person making the courses, and you didn't speak Turkish before, how did you make a course that taught yourself Turkish?

> We work together with some institutes of endangered languages to be able to teach them on our platform.

I assume this is how? Are you a platform for these institutions to provide Duolingo-style language courses? Can you possibly provide more details on who these orgs are?

Funny vibe code glitche in how an excersirce gives away the answer in a transaction of each question.

First question: Wie steht es um Ihr Greek?

Greek is obviously the english and not the german name of the language. But "Wie steht es um Ihr Griechisch?" wouldn't be grammatically correct either.

It's an absolute disaster in both romanization of Khmer characters and pronounciation. Simple words like 'arkun' are pronounced _very_ incorrectly and the romanization is incomprehensible.

I'm interested. What's the fundamental difference here, that actually pushes you to learn the language in a useful way?

Some questions:

"Listen to authentic native pronunciation in every lesson. Learn the correct accent and intonation from day one."

Can you elaborate on what this means? I currently speak Portuguese (Brazilian) and Italian. While the Italian audio seems fine, the Brazilian portuguese audio is not very good. It seems to be using Portugal's portuguese. And it doesn't sound "native". The audio for single words specially is not something I would recommend to anyone learning portuguese.

The landing page also makes these marketing claims but doesn't go further into any of them:

- "Our proven algorithm tracks every word you learn". Do you follow any learning methodology? What has been "proven" about your algorithm? Are their some stats?

- "Engage in dynamic lessons designed by language specialists." Who are you language specialists that have "carefully designed lessons"?

The one thing you have going for you is that I didn't have to give you my email to get started but the landing page doesn't give me any confidence that this app is better than Duolingo or other language apps.

On Russian, the explanations of why some answers were correct/incorrect didn't load (presumably an AI call failed?). Especially at lower layers, a good fallback would be a simple dictionary definition.

On Spanish, I did the placement test, then it asked which "dialect" I wanted. I selected Mexican, and was treated with truly excellent renderings of European pronunciation. I wouldn't have been mad if all it had was one set of pronunciation, and it's more frustrating to see the ignored option than to never have it at all.

As for the placement test: I got dropped into lesson 2 for Spanish. For comparison, I placed into Lesson 5 in Russian, where I actually got more incorrect answers. The Spanish placement test wasn't very deep, and I knew all the answers. It told me I got two wrong, so either the test is wrong or I just got punchy and hit the wrong buttons.

Recommendation: scale back on the ambition. Focus on getting the educational and product experience right with languages you know first. Be honest about data provenance and limitations.

Thanks for all the feedback, this filled up our backlog for surely a few weeks.

1. I selected "advanced level" for my target language. I expected real sentence. Instead I got a lot of "I am American" and "He is tall" type sentences.

2. In some cases when I was asked to select the word to complete the sentence, multiple options could be correct, but only one was recognized as correct by the program. Concretely, the format was "He is ______" and the possible solutions were "that" "Indian" "American" "comes from" and "French". Three of those options are perfectly grammatical, but only "French" was marked correct.

3. No offense, but this all has the hallmarks of AI slop, which I consider to not be an appropriate way to develop language learning tools, especially at an above-beginner level. Each language has different structures and complications and requires attention to different aspects of the language.

4. Above all, this app does not appear to differ from Duolingo in any substantial way, except that it's worse. If you're going to boast that your app is better than Duolingo, you should substantiate that with a concrete argument. Certainly Duolingo is highly flawed, above all in its total absence of formal grammar instruction which is something that even an AI-generated app should be able to do.

It doesn't seem to have any theme for each lessons either, which is my major bugbear about the new duolingo. (its really obvious in the more well loved languages like spanish)

I would start to enumerate the mistakes, but it's not even worth it. It's really terrible. Can't sugar coat it at all, sorry.

The problem is there, but a tool is just not the solution. The solution is to actually put in the elbow grease and learn what you need/want to learn.

Apps need to be dopamine fueled to work, and no one has fixed this problem yet.

How do you prevent gullible users from wasting their time and money on the app rather than learning languages?

From your testimonial that you learned Turkish do you at all mean to imply that a user of your app will have a higher chance of learning Turkish than if they didn't use the app vs say a conversation partner?

Why sell an ineffective product when a more effective one is free?

To quote you "I'm not going to pretend this replaces living in a country or having a conversation partner." This sounds like you believe a simple telephone call is superior to your app. If so why create it? Did you consciously decide to pray on socially anxious people or are you just following other apps blindly?

70+ languages and 700+ courses would imply a staff of people were required to create something like this (if it's of any quality), but it's a "side project"?

Strains credulity.

The demo leans heavily on "choose the words for the sentence", which avoids spelling/keyboard issues, and maybe generalizes around the problems of N->N language maps better. The "decoy selection" for multiple choice answers also isn't great - I am getting sentences mixed with numbers for the translation of "three".

It also has the Duolingo-esque audio "reward" sounds. I personally hate them, but a lot of people feel otherwise.