Qwen3.8-27B just built a COD-style game beating Gemini 3.8 Flash, GPT-5.6, Opus 5, and Grok 4.6

And the wild part isn’t even the game itself. It’s that a 27B open-weight model can generate something this ambitious while running locally on consumer GPUs.

FHILY👑Aug 175

Ranking Every Single AI Model From Worst to Best

This summer had so many banger releases like Qwen 3.8, Kimi K3, Opus 5, Fable 5, GPT 5.6, Deepseek v4 and like 100 others... But which one is truly the best in terms of price, usage, and consistent intelligence RIGHT NOW?

ashenAug 1717

I had Opus 5 make a clone of Little Inferno.

This is what it did in one shot!

Scott the VRNerd ☀️🌎🌑Aug 171

Opus 5 + higgsfield just fired the web designer who was making $8K/MO.

There’s a difference. unnecessary means the work disappeared. it didn’t - someone still decides the type scale, the spacing, the palette, the component system. that work matters more than ever.

GHOST 🌙Aug 171