Ran FlappyBench on Qwen3.8-Omni-Flash, DeepSeek-V4.1-Flash, and Gemini 3.8 Flash with the same design prompt.
🔹 Qwen 3.8 Omni Flash: 9/10 · $0.013 · smooth gameplay and cheaper 🔹 DS V4.1 Flash: 9/10 · $0.0089 one-shot with the lowest cost 🔹 Gemini 3.8 Flash: 5/10 · $0.205 ·
In addition to Codex/Claude Code
In addition to Codex/Claude Code, I think you can do most things if you have DeepSeek V4.1 Flash available, and if you can run Qwen3.8-Flash-Next locally even if it is slow. This is a nostalgic pagoda garden that I recently made with Qwen3.8-Flash-Next to check the operation after disassembling EVO-X2 lol…
[Gen Z AIVtuber] Mr. ZAI Japanese version 🇯🇵 This is my favorite voice on Elevenlab, but maybe because it's v2, the Japanese is a little weak.
Background: ChatGPT LLM:deepseek Voice reading: Elevenlab Loading comments: Wankome I spent about 3 hours on streaming and testing. Deepseek and Elevnlab together cost about $2.2
While Wow: Forever is in beta, I’ll be dropping hype videos made with my Asus Ascent GX10 and Hermes Agent.
Hogger doesn’t stand a chance when you gather the party to take him out! Warrior tanking, Rogue backstabbing, Warlock and Mage firing away, and the Holy Priest in the back
You have reached the end of the archive
All of deepseek