Live data from Hacker News

Launch HN: Issen (YC F24) – Personal AI language tutor

news.ycombinator.com

151–160 of 282 posts

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#151
post #118

Luis von Ahn spoke in the early 2010s—probably around 2014—at The LAB in Wynwood, Miami. He recounted how his fascination with crowd-sourcing led first to reCAPTCHA and then to his latest venture, Duolingo. He made it clear that his real passion wasn’t language per se, but building a crowd-sourced human translation service as a business model. At that point, Duolingo had roughly 24 employees—and, much to his surprise…

> (I had ChatGPT fix my grammatical errors and now this comment doesn't sound like me, sorry.) And it didn't correct "distrupted" to disrupted?

Nope

https://imgur.com/a/m3svUky

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#153

I learned Spanish to an advanced level (B2) many years ago with a combo of Duolingo, Anki flashcards, and real tutors. One of my biggest regrets is focusing too much on the grammar and vocabulary and not enough on having conversations with natives. I'm convinced it would have taken me half the time to reach B2 if I had focused more on conversations. I think this app is going to be really effective. Congrats to you gu…

[dead]

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#155
Congrats on your app and love it so far! Already sent it to over a dozen family members. Curious about a couple of things

- I see only two employees on LinkedIn -- how were you able to QA all these different languages with just two people?!

- I tried Urdu and the app did quite well. But curious why you have two female voices and not any male voice?

- I realize Sesame is a much bigger team, but curious what you think they are doing that makes their voices feel so real and seamless. I dont think they do multiple languages so I think you have a harder problem of course.

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#156
The website is a bit buggy (Safari). The session should start with a 'hi!' from the tutor ?? I got confused whether my mic was working, refreshed a couple of times until I prompted it myself. I tried it in my native language, Romanian: the speech to text is bad for Romanian and I got a random non-Romanian word within the first 30 seconds of using it (I assume it was meant to say "hello!") and gave up. For German, which I am learning: I agree with others it is too unstructured. Also the transcription for my speech was wrong, it didn't correct me on it and I got frustrated again.

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#157
post #72

It would probably be better to pick one or two languages, actually work with native speakers to make sure it's right. These "we cover every single language" tools get it like 75% right at best.

I disagree because of how AI is progressing and because there's tons of neglected language markets they can pick up. Obviously your approach can work too, perhaps better. But 95% of language learning tools don't support Thai (my target language) for example so I am an eager user for that reason alone. I think they'll be able to make a generalized curriculum and have the AI use it in all languages.

Most of the generalized curriculum stuff out there is crap because languages differ from each other in substantial ways. LLMs in principle should help here as they can use their knowledge of the structure of the language to modify, but we're just not there with context windows and thinking capabilities. They will need at least a per-language (ideally per language pair) system prompt that contains a rough outline of the curriculum.

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#158
post #94

Earlier quoted context omitted.

Why not finish, publish it to the store and get income if it was that straightforward? There's a long way to go between a toy application to demonstrate a product, and something on shelves actually selling. In other words, you can most often quickly tackle the concept or trivial parts of an app, but it's much harder to get a real product out, even if the implementation looks straightforward on surface.

That's exactly my point. This is at best a toy application driven by a prompt that many people will be able to extract and recreate. Putting the pieces together is easy and letting someone talk to an AI is not a particularly difficult problem. Creating magic and making people come back to learn the language is entirely different and I don't see anything magical here.

> Putting the pieces together is easy and letting someone talk to an AI is not a particularly difficult problem

Exactly! Not difficult, right? Making and selling a product out of it is called marketing. It is not rocket science, but many engineers can't grasp it.

GPT Wrappers are the new CRUD. There is no innovation in Trello, Jira and any other SaaS, they are just marketed products that thousands of people here in HN could code better, but they don't, because they are wasting their time pointing that other people's products are not a difficult problem to solve.

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#159

It's very cool, I'm enjoying playing with it. Feedback: The tutor pronounces some obvious things wrong that contradicts the words. Two examples: 気滅の刃 - it pronounced 刃 wrong despite the furigana being correct. It also kept pronouncing は as "ha" even when used as topic particle in more complex sentences. Edit: also observed 使い方 pronounced "saifou" - no idea what's going on there. It was in a mixed english-japanese mes…

May I ask which tutor you were using? The TTSs have different strengths and weaknesses. Good idea on the export, will add that to our to-do list.

Aoi (it was 1st in the list)

Re: Launch HN: Issen (YC F24) – Personal AI language tutor

#160
post #72

Earlier quoted context omitted.

I disagree because of how AI is progressing and because there's tons of neglected language markets they can pick up. Obviously your approach can work too, perhaps better. But 95% of language learning tools don't support Thai (my target language) for example so I am an eager user for that reason alone. I think they'll be able to make a generalized curriculum and have the AI use it in all languages.

My tool supports Thai, if you'd like to try it - https://nuenki.app . I added it at the request of a user, who seems to be happy with it. It's a browser extension that finds English sentences in webpages, and translates the ones at your difficulty level into the language you're learning.

That's a pretty sick idea. Unfortunately I presume it involves sending your browsing data (e.g. page contents) to the server?
Post reply on HN