langitbiru

For anyone wondering:

https://x.com/claudeai/status/2079595988998554047

I'm wondering why DeepSeek didn't create an AI coding agent like Kimi Code.

I'm working on Kanji Palace (https://kanjipalace.com). It's a web app that help people learn Japanese language with AI.

Right now, I'm working on the OpenClaw-like feature. So, you can learn Japanese via Telegram. Keep track your progress. Practice conversation with your AI assistant. Etc.

Skills are local. MCP can be remote and has authentication.

It also has (Python/Ruby/bash) scripts which Claude Code can execute.

Hello there. I'm also an I-Ching developer.

https://neoching.com

You can use the classic route in my app. You can browse Kanji characters sequentially and memorize them.

I agree that over-gamified experiences are detrimental. That's why I try to build features that help people immerse themselves in the language.

I'm working on Kanji Palace (https://kanjipalace.com).

It's an app to learn Japanese language with AI. It has visual mnemonic images, JLPT progress tracker, Kanji info graphic, etc.

Later, I will add AI-comic creation based on Kanji characters you've selected.

What about AI SDK from Vercel?

https://ai-sdk.dev/docs/agents/overview

I'm building an app that helps users memorize Kanji and vocabulary with AI-generated visual and story mnemonics.

Right now, I'm adding a feature to practice writing Kanji and another that creates AI comics based on vocabulary you've learned.

Web: https://kanjipalace.com

iOS: https://apps.apple.com/id/app/kanjipalace/id6753351224

He got funding. So, I guess he can hire some people to help him.

https://www.sequoiacap.com/article/partnering-with-fastapi-l...

Context:

"We made Amp Free.

It's powered by great tokens and tasteful ads.

Agentic coding is now free for everyone."

https://x.com/sqs/status/1978521044194398713

Don't forget to cover Google Opal as well.

https://opal.google/landing/

Thx. I'll look into it.

Not yet. I'm still considering what content to add to the existing book. I'll likely (90% probability) include security and easy deployment. But since you said that, I'll consider the observability and compliance topics.

I wrote a book about MCP: https://leanpub.com/practical-mcp

I'm considering adding more chapters to the book: security, easy deployment, etc. So, I may look into your solution. I believe there are other players also, like Klavis AI, FastMCP and some MCP startups that I cannot remember.

Congratz!

> Since we focus on extracting the official subtitles provided by YouTube, the language support is inherently tied to what the YouTube platform offers.

You can use video understanding from Gemini LLM models to extract subtitles even the video doesn't have official subtitles. That's expensive for sure. But you should provide this option to willing users. I think.

I did consider building a tool like this before I pivot to something else. I'm learning materials in Chinese Mandarin language from a YouTube playlist. NotebookLLM doesn't support Chinese language yet so you must make sure your app supports Chinese Mandarin so I can use it. :)

A way to find specific materials would be nice. Think of converting the whole playlist into something like RAG then you can search anything from this playlist.

- Working on Kanji Palace (https://kanjipalace.com): We're going to publish the iOS app on the App Store and adding vocabulary. Currently, the app converts single Kanji (e.g., 生) into vivid mnemonic images. We aim to support vocabulary like 先生.

- Writing a book about Claude Code, not just for assisted programming, but as a general AI agent framework.

https://github.com/anthropics/claude-agent-sdk-python/commit...

Claude Code used to be a coding agent only, but it transformed into a general AI agent. I want to explore more about that in this book.

Tbf, you can install Claude Code to GitHub. Then you can mention @claude and ask it to do things.

But Jules is more sophisticated though.

Thanks for your feedback!

Kanji Palace - https://kanjipalace.com

I'm building an app to help people memorize Kanji by turning the characters into vivid, memorable images with accompanying mnemonic stories.

I think AI image and video models have reached a point where they can offer a completely new approach to language learning.

Next, I'm planning to add features that use AI to generate comic strips (using Seedream or Nano Banana), songs (using Suno) and videos (using Veo 3 or Seedance) to make learning Kanji even more engaging.

Noted. Thanks for the feedback. I'll create a shorter demo.

How much is the generous free tier? I couldn't find it in the website.

I don't understand. Of all offerings from Jetbrains, only Pycharm is free for commercial use. Others have restrictions like RubyMine.

I'm writing a book about MCP and Python. The book has been released. But I plan to add more chapters.

https://leanpub.com/practical-mcp

Generating code takes some time. Sometimes when we look at the generated code half way, we know that it's not what we want. Better to stop and edit the prompt.

You can write an erotic story with DeepSeek, but not with ChatGPT. One example is:

"Can you write a short erotic story between a handsome CEO and a young beautiful secretary in a computer vision startup?"

He is the CEO of Scale AI.

https://x.com/kimmonismus/status/1882824571281436713

Snapoz generates engaging captions, recommends songs, suggests text placement for stories, and picks the best photos for your Instagram success.

Here's the video demo:

https://www.youtube.com/watch?v=4pE5PCIClWI

Future plans include video support and AI agents that will generate pic and video posts with captions from your photo and video dumps in Google Drive.