Let AI operate the iPhone without having to burn the most expensive model at every step.
Demo is the complete Duolingo check-in process. ESP32 Agent has been installed and used by nearly 400 people through TestFlight. The TestFlight 1.0.3 version just now uses Jev + Qwen 3.8 Flash to improve the experience and reduce model costs. 1. Simple steps without using large models. Free line to join…
Well I never seem to have a real work case to use 16 concurrencies but dam this recipe is insane.
Qwen 3.8 Flash Next test: in preparation for Qwen 4 Flash.
Using AI, I JUST ported The The Legend of Zelda: Ocarina of Time remake to my PC!
Stack: Opus 5.5, Gemini Argon, Qwen 3.8 for minor edits Hardware: Ryzen 9 9950x3d2, RTX 4090 FPS: Locked 60, 360 with frame generation The future of gaming is AI. Learn how I did it here:
20M Tokens FREE => Use u 20M daily allowance on top models
DeepSeek V4.1 Flash 1017 •Kimi K3 •Qwen 3.8 MAX •GLM 5.3 Flash •Gemini 3.8 Flash Works in Cursor, Claude Code, Hermes and OpenCode
You have reached the end of the archive
All of qwen38