Kotoba Dojo
Train your words. Command any AI
What it does
Kotoba Dojo is a gamified training ground for precise wording. You see a reference image → describe it in your own words → an AI regenerates the image from your description → you get scored on how close it got. Rank up from white belt to black belt. 22 languages. Credit system. Sign in with Apple/Google, Stripe, GDPR account deletion. Built by a solo founder with zero engineering background, using only AI coding agents. 16 days, ~40 hours of directed work, from blank to production.
Train your ability to communicate with AI through a game. Reach Level 100, then enter Ninja Training to build something real and earn your certificate.
Your account has been deleted. Thank you for training with us. Describe a reference image in your own words → an AI draws what you said → you're scored on how close it got. A training game that sharpens how precisely you put things into words — and how well you prompt any AI. You don't need to memorize prompts. You need to see — with your own eyes — what your words actually produce. Kotoba Dojo turns that into a game. AI courses hand out "magic prompts." They work once, then your situation changes. The prompt was never the problem — you were vague, so the answer was too. This isn't prompt engineering. It's knowing what you want, precisely enough that an AI can act on it. Engineer or not,…from kotobadojo.letiziainc.com
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com