Essential insights from Hacker News discussions

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

Focus on Not Gamifying Language Learning

A significant theme in the discussion is the perceived downfall of existing language learning applications due to excessive gamification. Users express relief that the new app is not heavily gamified, with some drawing a direct contrast to their negative experiences with platforms like Duolingo.

  • "Thank you so much for this. Duolingo is literally unbearable because it's so gamified. I'll try it out later." - thinkingtoilet
  • "I appreciate your comment about gamification. I’ve kept a streak alive on other apps for no other reason than keeping a streak alive. Not learning a thing." - johncole
  • "Yeah, this is the biggest gripe we hear about much of the existing language learning landscape. That they're effectively gaming apps masked as language learning apps." - antonaf

However, there's a counter-argument that gamification, while not directly tied to learning effectiveness, can be crucial for user retention and enjoyment, which are enablers of learning.

  • "You should still gamify it. Gamification is orthogonal to whether the tool actually works and positively correlated with whether the user actually uses it." - 55555
  • "I would argue that games are a great analogue to language learning as well. Contrary to our ideals, people do like to enjoy themselves and are more likely to pick an activity they enjoy than one they don't. Games and puzzles are able to present frustration as enjoyment (provided there is appropriate reward and perceived growth) making them great tools for learning." - Velorivox

Challenges with Individualized Learning Paths and App Optimization

Several comments highlight the issue of language learning apps being optimized for the "global population" rather than individual needs, leading to a "mediocre" experience over time. The lack of individualized learning loops and the repetition of lessons are cited as major drawbacks.

  • "The app is optimized on the whole population, not on individual level. They even publish papers on global optimization." - vjerancrnjak
  • "These kinds of learning apps are destined to become mediocre over time. The learning metric is so easy to capture, the learning content so easy to produce, yet no one has an individualized loop to make learning work well. For example, I'd press "Training" on Duolingo, and would get nowhere. Same lessons all of the time. Bread and water." - vjerancrnjak

The developers acknowledge the need to improve the beginner experience, noting that the current setup is more tailored to intermediate/advanced students.

  • "Thanks for the feedback. Yeah we need to improve the beginner experience, it's more tailored towards intermediate/advanced students at the moment." - mariano54

Users expressed a desire for a more structured and guided learning experience, moving beyond random topic discussions, particularly for intermediate learners.

  • "My thinking is - I can have unstructured conversations with Advanced Voice Mode or in real life here in Sweden. What I'd really appreciate is a guided learning experience taking me up from intermediate/slightly above intermediate to fluent in the most efficient possible way (as opposed to just having us 'ramble' about random topics of my own choosing)." - drakonka

Broad Language Support and Testing Transparency

The app's broad language support is praised, with inquiry into how this was achieved so quickly. The developers attribute this to leveraging LLMs and TTS systems that natively support many languages, and their strategy of relying on languages with low word error rates in transcription and official LLM/TTS support.

  • "This actually looks pretty neat. How have you been able to achieve such broad language support so quickly? How widely have you tested your supported languages on native-speakers and learners?" - xmodem
  • "The STT and LLM support many languages out of the box. For TTS we use multiple providers based on their strengths and weaknesses (for example minimax is great for Chinese)" - mariano54
  • "The language support is based on the intersection of the languages that have low word errors rates in the transcribers, as well as officially supported by LLM/TTS (like gpt4.1, eleven labs etc)." - mariano54

However, there's a strong user demand for clear communication regarding the level of support and testing for each language, emphasizing the potential for user frustration if they are mis-taught due to insufficient testing.

  • "Right - I think it would be appreciated by your users if you could at the very least made it clear from the outset how well different languages are supported and what degree of testing you have done. Certainly if your product were to mis-teach me important details, and I were to then find out that you had spent less time testing than I had spent learning, I would be quite angry." - xmodem

Technical Implementation and Voice Quality

The technical aspects of the app, particularly the seamless integration of STT and TTS for multilingual conversations, are noted positively.

  • "Yes, we've spent a lot of time getting the STT and TTS to work seamlessly in multilingual, it works pretty well!" - mariano54

A discussion arises about the choice of voice API, with a user questioning the use of a potentially less advanced voice API compared to Gemini's direct offerings. The developers explain their reasoning, citing intelligence degradation with context, higher costs, and UX considerations related to latency and interruptions. They also express a preference for Eleven Labs voices and anticipate future improvements in voice-to-voice models.

  • "Why not use the Gemini flash voice-api directly instead? Cost? I ask because from the demo, the tutor's voice seems mechanical. I've played with the gemini voice api and it's quite impressive for conversation with low latency, I'd say perfect for your use case. It even switches languages if I say "Okay, let's talk in $foo language"." - akshayKMR
  • "Multiple reasons (which also apply to openAIs realtime API): - it's less intelligent than the non voice apis - intelligence degrades even further with lots of context - more expensive - latency is not a free lunch, it comes at the cost of more interruptions from the tutor, which is a really bad UX. We prefer to interrupt less and have higher latency" - mariano54
  • "Also, we prefer the eleven labs voices, but there is definitely varying quality. I'm guessing later this year or next, the voice to voice models will become good enough, and we will switch over." - mariano54

User Experience Issues and Feedback

Several users reported technical difficulties, including account creation loops on the web version, which the developers are investigating.

  • "Tried the Web Version. Started, then tried to create an account, but it kept looping, informing me that my email address does not exist in your system. Well, the “Create New Account” got kicked off and gets me in a loop of “Do not Exist”. I just went through the whole process again, and I'm back to the beginning. I’m going to assume this works better on the App." - Brajeshwar
  • "Unclear what issue you hit, we'll look into it. Thanks for sharing." - antonaf

Other minor UI issues were noted, such as FAQ boxes not expanding.

  • "Those FAQ boxes on the main page don't expand?" - 4b11b4

Privacy Philosophy and Data Storage

A user inquired about data storage and the app's privacy philosophy. The developers clarified that messages are stored, but not audio. They also store session summaries and user fact summaries in AWS, with the ability for users to delete their accounts to wipe their data, though session deletion is not yet available.

  • "Do you store conversations? And what's the general privacy philosophy behind the app?" - I_am_tiberius
  • "We store the messages, but not the audio. We also store session summaries and a "user facts" summary that gets regenerated after every session, based on all session summaries, everything in our AWS DB. You can delete your account at any time to fully wipe all your data, but there is no way to delete sessions ATM." - mariano54

Disruption of Traditional Language Learning Platforms

There's a sentiment that current learning platforms, including Duolingo, are ripe for disruption, with this new app being seen as a potential catalyst. The historical context of Duolingo's origins as a crowd-sourced translation service and the broader trend of established platforms facing disruption were mentioned.

  • "Today, it’s not only easier than ever to launch a platform to challenge Duolingo, but its core product—its crowd-sourced human translation service—has been disrupted. This morning, I found myself thinking about how all those decade-old learning platforms—like Coursera, as reflected in its ever-falling stock price—are being disrupted. Your product looks awesome and I hope you disrupt all the language learning platforms. Thank you for sharing." - dataviz1000