dkaleta

Joined 9 years ago

Karma
55
Submissions
14
Member since
May 27
Engineer, biker & writing dilettante.
View on Hacker News

Recent submissions

Comment · 1 year ago
I believe we can have a beta release in September, and yes, we plan to open-source the editor.

PS. I’m stealing the ‘antidote to “vibe coding”’ phrase :)

Comment · 1 year ago
Yes, the idea is to ‘speak/write’ to the local model to fix those little things so you don’t have to do them by hand. I actually already have a fine-tuned Qwen model running on Apple’s MLX to handle some of that, but given the hard YC deadline, it didn’t make it into the demo.

Eventually, you’d say, ‘add an additional layer, TopicsController, between those two files,’ and the local model would do it quickly without a problem, since it doesn’t involve complicated code generation. You’d only use powerful remote models at the end.

Comment · 1 year ago
Comment · 1 year ago
Hey YC,

I've spent a lot of time building something I wish I'd had when I was learning Spanish: an app that lets intermediate learners practice with real, interesting content. When I studied Spanish, I often got frustrated because native content had too many words and expressions I didn't understand.

Thanks to recent AI advancements, it's finally doable—but getting it right was tricky. It took setting up a multi-step pipeline and fine-tuning several AI models to make it work smoothly.

Here's how it looks in practice, turning a Spanish news article into a personalized language lesson:

- Simplify the article to match the student's current skill level. - Add language elements the student is currently studying (like the past tense or certain phrases). - Include specific vocabulary words the student is learning to reinforce them in context. - Use another AI model to tokenize and lemmatize the text so the app can accurately recognize each word's context and offer quizzes, definitions, and comprehension checks. - Automatically link words and expressions to detailed dictionary entries. - Generate high-quality audio with ElevenLabs for authentic listening practice.

There are a few smaller steps involved too, but those are the main ones.

I think Topics is the first app to create fully personalized, contextual language lessons directly from current news content.

I'd love to hear your thoughts! If you're interested in trying it out, send me a PM—I can give you an access code in exchange for your feedback :)

Comment · 3 years ago
Yes, so far we’ve made videos for beginner and intermediate students. None for advanced.

It sounds like you would be a good fit for advanced videos or perhaps you should start watching content made for natives (real podcasts, Netflix etc)?

Comment · 3 years ago
Comment · 4 years ago
Some people mentioned that the translation/conversation can feel pretty off. But there is a much more fundamental problem here. If you want to be fluent, you need to spend hundreds of hours speaking the language. It is really difficult to speak for hours to a machine that doesn't express any emotions and is not excited about anything.

Humans, when speaking the language, connect to other humans through emotions and feelings. That is what gets us going. That is what keeps the conversation interesting (even for intermediate students).

This is the same reason why ads from Apple always show how family meets, or a kid scores a goal in a match and not just simply says "1.8GHz, 4GB ram" that only speaks to our neocortex.

That's why unless computers pass the Turing test, it is unlikely this will "enable people to talk their way to fluency".

I do agree though it is a cool tech.

Comment · 4 years ago
I’m 34. I don’t think age matters that much. What matters the most is not even the method you use but the time spent with the language.
Comment · 4 years ago
Comment · 7 years ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton