dkaleta

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 :)

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.

Since this topic is closely related to my new project, I’d love to hear your opinion on it.

I’m thinking of building an AI IDE that helps engineers write production quality code quickly when working with AI. The core idea is to introduce a new kind of collaboration workflow.

You start with the same kind of prompt, like “I want to build this feature...”, but instead of the model making changes right away, it proposes an architecture for what it plans to do, shown from a bird’s-eye view in the 2D canvas.

You collaborate with the AI on this architecture to ensure everything is built the way you want. You’re setting up data flows, structure, and validation checks. Once you’re satisfied with the design, you hit play, and the model writes the code.

Website (in progress): https://skylinevision.ai

YC Video showing prototype that I just finished yesterday: https://www.youtube.com/watch?v=DXlHNJPQRtk

Karpathy’s post that talks about this: https://x.com/karpathy/status/1917920257257459899

Thoughts? Do you think this workflow has a chance of being adopted?

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 :)

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)?

used Duolingo to help me learn Spanish, and I was struck by how artificial it is.

I've had the same experience with Duolingo and long story short decided to experiment with what would be the best way to learn the language if you're not advanced enough to consume content for natives. I wanted to created something that would have the same value as content for natives (interesting and real), but would be comprehensible to non-advanced learners.

Just last week I opened up access to my app (with over 50 videos) to Beta testers. If anyone is learning Spanish and would like to try it out and give me feedback, I would appreciate it.

Obstino U is an app that mimics a real university where you take classes about the things you are interested in like climate change, the history of china, cognitive biases, diets, investing, etc, but you do it in the language you want to learn.

Simply put, you learn things you are interested in and in the process, you learn language mostly subconsciously.

We use simplified language, gesticulation, and drawings to convey powerful and rich stories so that even beginner students can understand them.

https://www.obstino.com

EDIT: This is an iOS app only for now.

EDIT 2: I just added a sample video we make on YouTube in case you don't want to install the app but want to take a look: https://youtu.be/N2fiVLUJGvM

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.

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.

I learned Spanish, too, in about 12 months to dogfood my new app for learning vocabulary (which I just recently launched) [0]

Even though I made an app that helped me along the way to learn words, I don't believe in a single app/book/approach for learning a language. You need to expose yourself to A LOT of different language materials.

I was learning for about 2h a day, 6 times a week. I would read articles, books, websites in Spanish. I would watch YouTube videos [1]. I would read news, initially for beginners [2] and later regular [3]. And most importantly, I would have 4-5h a week itakly conversations.

After 6 months I understood quite a lot, but couldn't speak almost at all. Then magic happens and 6 months later, I was having a normal conversation (though still with some errors) about any range of topics: politics, global warming, travel, engineering etc.

I believe the key for me was to read a lot of books which were interesting to me. For example I read Bill Gate's book "How To Avoid A Climate Disaster" in Spanish, as well as about ~8 others in the first 12 months.

[0] https://www.obstino.com

[1] https://www.youtube.com/c/DreamingSpanish

[2] www.newsinslowspanish.com

[3] https://elpais.com

When you unlock your Mac with an Apple Watch, the OS makes sure the watch is actually close to it by measuring the distance it takes the signal to travel to the device. Why won't car manufactures do that? Is there any reason?

https://bgr.com/2016/06/27/macos-auto-unlock-security-apple-...