I vibe-coded an AI Dota 2 inspired RPG in 3 months.
Zero hand-written code🧵 Logic: Claude Opus 4.8, Cursor, DeepSeek-V4 World/Physics: Seedance 2.5, Kling 1.5, Hailuo AI, Seedream 5. Look at the amazing result👇 ⬇️
SITUATION EXPLAINED: Alibaba’s Qwen 3.8 Flash beats DeepSeek V4 Flash and Opus 4.6 Max on most tasks, at just $0.16/M input tokens.
It leads DeepSeek V4 Flash and Opus 4.6 Max on most tested tasks, at $0.16 input and $0.47 output per million tokens • 125B total parameters
I took the time to update the Deepseek Harness plug-in, and Dockyard DSH has reached version 0.1.2.
One-click installation: npx -y dockyard-dsh/install@latest
Created this retro arcade-inspired landing page for an AI consulting website with Qwen3.8-Flash.
125B parameters + 51B N-gram embeddings, with only 6B activated per token. It also reportedly outperforms Alibaba_Qwen 3.8-27B and DeepSeek-V4-Flash across most benchmarks. I
You have reached the end of the archive
All of deepseek