Launched this week
Neuralingo Language Learning
slowly inch your way to mastery: try, fail, learn, get good
104 followers
slowly inch your way to mastery: try, fail, learn, get good
104 followers
6 learning modes cover - in theory - all you need to know to truly get good at a new language. Reading, writing, listening, pronunciation, conversation and language understanding. Each exercise uses vocabulary and grammar that you're slightly insecure in, so you can make mistakes, understand why and get a bit better every day. The learning algorithm is based on the "forgetting curve" and "desirable difficulty" research from neuroscience.
Neuralingo Language Learning
I know that ProductHunt launches are overwhelmingly AI-based now, but Neurolingo is, after signing up, doing the assessment, and even paying for a plan(!) a really good example of why "vibecoding" and LLMs in general are not suited to language learning (at least not at the moment).
It's why I canceled and uninstalled DuoLingo when they said they were an "AI-first" company.
This review/comment is kinda long, so the TL;DR here, from a paying user who intends to cancel is: DIY flash cards are a much better use of your time and money.
(As a note: all images below are screenshots of the app, in browser, doing something frustrating or confounding.)
The session was maddening. First, Lex insisted on things like accents for French, even though those are not native keys on an English keyboard. I was able to move past this with Lex, but it's a stupid oversight unless we're specifically working on an accents exercise.
Lex would ask me if I wanted to explore a specific pain point further, or continue the lesson. Any response ("continue" or "let's work more on article-noun gender agreement") would comply...and then immediately jump into an unrelated lesson and/or ask me to translate Je voudrais un café et un croissant. When I pointed it out, it said it had some system confusion.
In the post-lesson report card (mistake review), it marks responses to the user's confusion as ACTUAL MISTAKES, which is mind-bogglingly stupid.
Another "mistake" was rightly evaluated as a mistake in the post-lesson, but in the lesson was marked as "ABSOLUTELY CORRECT!" which is confusing, frustrating, and just...bad.
The constant move back to Je voudrais un café et un croissant created a confounding interruption of the flow of the lesson, ensuring that almost nothing would stick. Sincerely, before the lesson self-ended (which...why?!) it had asked me to translate Je voudrais un café et un croissant no fewer than half a dozen times, completely out of context, and without any relevance to the lesson. That is probably the only thing I remember confidently, other than the sycophantic insistence that I was "absolutely correct to be frustrated" and "translated that perfectly!" (when I had not).
The pre-start evaluation put me at A1, but the session for some reason was in A1, and the pre-start analysis had me at 10, but this hour long session is saying I'm now at 11, even though it's a full half-level below where I should've started?? Also: This is a minor gripe, but I didn't spend 108 minutes in this lesson (it was about 50, and then the lesson auto-ended without warning).
Who is this little bit of "sage wisdom" supposed to be for? Why are you shipping a language app with a formulaic fortune cookie saying?
The mistake overview is actually just worthless, because half of these just were not mistakes, and many of the others were me attempting to troubleshoot Lex's condescension (which was especially high contrast when Lex was just dead wrong, e.g. The root cause of your mistake is....) even if the mistake was something like noun gender, which is learned through rote memorization, and cannot be divined by looking at the word. For example, none of the "mistakes" listed as mistakes were actually mistakes. The evaluation is just hallucinating.
I gotta say that it is deeply agitating for this to be the outcome here. I could've made this in ChatGPT back when OpenAI launched the "custom GPTs" feature in like, 2023, and it would've been just as if not more effective. I have very little confidence that NeuroLingo is ready for prime time in any sense of the word "ready," and, aside from the reasonably attractive UI, I'm not confident in anything about NeuroLingo.
Importantly here, I'm not confident that Lex/the product even has a good enough internal understanding of language or how languages are learned to believe that the lesson I just spent an hour in was accurate on a language/lexicon/vernacular level.
In almost any scenario I can imagine, I would've been much better off using Google Translate to make personal flash cards, and just memorizing them–and I'm saying that with the understanding that Google Translate isn't particularly great.
I would say "good luck" but I honestly feel like this product might be actively deleterious to users' attempts to learn a language.
Neuralingo Language Learning
@david_joseph Good morning David! Thank you for taking the time to write such an extensive review. Something went majorly wrong in your session. I had fixed the "mistakes recorded in English" issue before - it seems not sufficiently. The unrelated additional exercise and the "Je voudrais un café et un croissant" many times is new to me. Wild! I agree with you - that those things are severly disrupting the learning experience. I'd push back slightly on the accent comment, LEX is supposed to be thorough and accents are a part of the language. Did you find setting your keyboard to French worked?
Re: Paid plan: You are obviously not satisfied, so please send me an email to julius@neuralingo.academy and tell me where can I send the money back to. Please also remember to cancel the subscription, otherwise it will go on monthly.
A user having an experience like yours was the thing I was most afraid of. Now it happened and in some way it had to, to help discover those issues. Thanks for the brutal honesty.
Julius
Most language apps make things too easy so you feel good but don't actually learn. How many languages does it currently support, and does the pronunciation mode work well for non-Latin script languages?
Neuralingo Language Learning
@ben_gend I agree, and I think these apps are targeting people that have only lukewarm interest in learning a language. It's more a "get the feeling of being in Italy while being at home" kind of thing. So, it becomes entertainment more than education. A friend in Germany said "Duolingo is not really working, but it's the most productive thing I do with my phone". I am not sure, I hope we can find a way to navigate this in marketing.
Re: pronunciation mode:
AzureSDK is used for this and it is remarkably accurate. But I wouldn't call the pronunciation mode good overall yet for any language, because so much depends on the calibration between the user's voice and the speech tool. E.g. We have a Portuguese native speaker who is learning German who has a hard time with the consonants, which makes her pronunciation very different from the target. It works and it is helpful, however the Expression mode (translating into the target language) is where most of the actual understanding is gained. Once people understand the language they can listen to it. Once they can do that, they can pronounce it (fine-tuning).
What language do you want to learn and have you tried the pronunciation mode for it already?
Re: supported languages: I am copy/pasting from my earlier comment:
We use LanguageTool (Docker) and deepL for verification of the AI responses. We use AzureSDK for the pronunciation analysis and GoogleSpeech for TTS. So, the limiting factor is what these tools support.
The main languages are: English, Spanish, French, German, Italian, Portuguese, Japanese, Korean, Mandarin Chinese, Vietnamese. There are others, like Swedish, Arabic, Russian, Greek... which are supported, but not from all tools. E.g. LanguageTool doesn't support Swedish, so you may get a few more AI hallucinations. Farsi doesn't have a great TTS voice available. And so on..
For the beta, we have left the list of languages quite large to see how the users' experiences are. Perhaps we need to remove some in the future.
Good luck with your launch!
Learning a language properly through apps is really hard (I'm struggling to learn German with Duolingo actually), and I think your app can really solve this problem!
I'm curious to know more about the method you talk about in the website: did you do some deep research on neuroscience or are there neuoscientists in your team who helped you develop the app?
Neuralingo Language Learning
@pamela_arienti Thank you Pamela! Interesting that you're learning German - I bet you are not loving the grammar cases (Dativ, Akkusativ, ...). It would be interesting to hear your comparison between your progress made from Duolingo and neuralingo.
The core neuroscientific findings are that we remember very little when we passively consume material and significantly more when doing it actively. There are 3 key active learning methods with increasing effectiveness: group discussion, learning by doing, explaining (most effective). We basically eliminated all the passive ones and replaced them with active ones, e.g. the AI does not tell you the mistakes right away, but it asks you to go through what you wrote and compare it to the correct solution and spot your mistakes yourself.
Desirable difficulty is also a key neuroscientific concept: Each exercise is just a tiny bit more difficult than the previous one, so that you're making about 1-3 mistakes. You're always a bit outside your comfort zone, but it's challenging, not overwhelming. (I think that's very important, because when we see progress, we continue, but if we get overwhelmed - which we often do in traditional language learning - we stop)
The neuroscience that exists goes far deeper than we've applied in neuralingo currently. I did it myself, but I am hoping that someone with a neuroscientific background will join the advisory board.
P.S. Perhaps we should add you to our free neuralingo German group - 8 German learners from Chile, Peru, Turkey, Iran, Philippines - they are going to Germany for work. You could set meetings with them to practice.
@oldcarnewradio @Neuralingo Language Learning
Hi Julius! It's my first time to know AI product via makers' real story which's really cool and vivid. Here's my perspective from not professional but real language learner.
1. 🤩👍Good aesthetic taste which makes me have attention and intent to go deeper! THAT IS IMPORTANT FOR language learning App. You know what I mean.
2. Honestly I have left my Duolingo cuz I do not need a game app which only use one language explaining another. 😓What I need to learn is a vivid and like storytelling bridge between cultures not only languages. Neuraligo really delivers a new learning experience.👍
3. I wonder if you guys develop speak features it will be much more convenient.💬
Neuralingo Language Learning
@laura_yang1 Hi Laura - Thank you for your kind words! Glad you like the UI - it cost me a lot of nerves to set up - it was either too techy or too academic 😃
That's exactly the position we want to develop in the market -- the language learning platform that actually works, not a game. Please share updates about your progress - that's really the only goal neuralingo has. You can use the feedback button on any page or via email to julius@neuralingo.academy.
Re: Speaking feature: Have you seen the speaking/conversation mode? You can hold a real-time conversation, either in writing or by speaking. What I've learned from the 1:1 tutoring over the last years is that the most important progress happens in the Expression mode (translating into your target language). Example: Sometimes students ask me to do more listening exercises, because they say they cannot do them well. Then we do them, and they don't do well again. So they think they just need to do more of them. But when we give them the same text from the listening exercise to read - and they cannot understand, then how can they expect to pass the listening exercise?
My point is: I know it's a bit boring, but if you can, spend as much time as possible in the Expression mode to build good language understanding.
What language are you learning?
First of all, congratulations on the launch!! This is a really impressive learning project. I’ve started using it and so far, the experience has been great!
One thing that genuinely stood out to me was the analysis after the assessments. I’ve tried quite a few language learning apps, and I can confidently say this is one of the best feedback systems I’ve seen, really insightful and helpful.
If I could suggest one improvement, it would be the textarea in the “Assessment with Lex” section. Since the input size is fixed, it becomes a bit difficult to review longer responses. I tend to write more detailed answers, and navigating through them isn’t the easiest after finishing.
I’m about to start the sessions next and will definitely share more feedback if anything else comes up. Congrats again on the launch 🚀
Neuralingo Language Learning
@matheusdsantosr_dev Thank you Matheus! I am happy to hear about your great learning experience in the assessment! We've had one user where something went super wrong in the sessions and I'm hoping that wasn't a general bug. Please let me know how it is for you. Email is open at julius@neuralingo.academy.
Thanks for the feedback on the textarea - will fix!
Seeing this at a really good time as I am trying to polish up my Swedish! Seems like an awesome application, congrats on the launch! What languages do you support atm?
Neuralingo Language Learning
@tom_blk Wow, Swedish is interesting. I was on an exchange year in the US once where I lived with a Swedish room mate. That was when Sweden launched Spotify and no one knew what is was yet 😃
Thank you for your kind words. We support Swedish, and you would be the first student - so it would be interesting to hear your thoughts.
Re: supported languages: We use LanguageTool (Docker) and deepL for verification of the AI responses. We use AzureSDK for the pronunciation analysis and GoogleSpeech for TTS. So, the limiting factor is what these tools support.
The main languages are: English, Spanish, French, German, Italian, Portuguese, Japanese, Korean, Mandarin Chinese, Vietnamese. There are others, like Swedish, Arabic, Russian, Greek... which are supported, but not from all tools. E.g. LanguageTool doesn't support Swedish, so you may get a few more AI hallucinations. Farsi doesn't have a great TTS voice available. And so on..
For the beta, we have left the list of languages quite large to see how the users' experiences are. Perhaps we need to remove some in the future.
@oldcarnewradio Sounds good! Makes sense that you'd be limited by the underlying tools, but awesome that you are still offering the limited languages with a disclaimer! I'll check it out!