I gave Gemini 4 Argon 8 reference images.
One night later: a 3D Paris around the Eiffel Tower. Day turns to golden night, people walk, bikes and pigeons pass by. It runs in your browser.
$48.97 · 3 h 24 min of agent work · OpenCode + Blender + Three.js
Walk it yourself 👇
Free to explore, works on iPhone: kartit.net/games/paris-3d/
Which city should Argon build next?
Download: anvilterm.com
It runs the official CLIs in real terminals and never sees your login
I asked a stealth AI model to fingerprint its own tokenizer. 🐰
Space Bunny Alpha's token counts match MiniMax's tokenizer exactly: 18/18, zero error.
Its reasoning about the result: "The model is Claude."
Models can copy each other's style, and even identity. They can't copy a tokenizer.
The full build in 5 minutes, every prompt and what broke: youtu.be/-5MUGPm92m8
The full build in 5 minutes, every prompt and what broke: youtu.be/-5MUGPm92m8
Play it free, your phone can be the controller: kartit.net/games/turbo-kartz…
Every prompt I typed, on screen, start to finish:
youtu.be/hzfClwZ4UHQ
Replying to @sama
your post got me thinking about the adventure games I grew up with. I used GPT‑6 Astra in Codex to build this Monkey Island-inspired playable prototype.
Seeing Mara walk, talk and solve puzzles still feels surreal. Rough edges included 🙂
Play: lantern-cove.akartit.chatgpt…
You said "proactive." So I gave it a mouse.
Opus 5 drew this in MS Paint. 67 strokes, 753 drag
events, on a Windows VM it had to ask permission
to touch first.
No image model. Just a cursor.


