How I Talked a GPU Owner Out of Building a Token Factory Over Dinner
GPUs plus open-source parts do not make a token factory. Each layer hides 10–30× efficiency gaps. Tokens are commodities; TSMC-style neutrality wins.
13 min read
Latest Posts
All Posts →
I Paid for a Top-Tier Model. It Got Dumber and Marked Me
Codex GPT-5.5 clusters reasoning at 516; Claude Code secretly marks Chinese users. When cloud AI silently degrades, open-weight self-hosting is the hedge.
14 min read
The Strongest Model Just Dropped, and I’m Not 'Qualified' to Use It
GPT 5.6 looks strong, but only ~20 U.S.-approved partners can use it; I realize intelligence you can buy is already fair, while permission is the real gap.
7 min read
Projects
All Projects →
GoAI InferenceMCPK3SFleetOffline-first
AIMA — AI Inference Managed by AI
Make AI inference deployment as simple as installing an app. AIMA automatically detects hardware, selects optimal configurations, and deploys with one click, turning every machine into an AI inference node.
C++HIPROCmAMD Ryzen AIWindowsLLM InferenceOpenAI API
AIMA AMD395 Qwen3.6 35B Windows Engine — Native Windows Inference
Native Qwen3.6-35B-A3B BF16 inference on AMD Ryzen AI Max+ 395: 8K prefill 2,126 token/s, decode 30.55 token/s, 131K prefix-reuse scenario TTFT 8.59s.
PythonAI AgentDevOpsCross-platformCLI
AIMA Server — AI-Powered Remote Device Operations Platform
Say goodbye to SSH and manual troubleshooting. Connect devices with one command, describe requirements in natural language, and let the AI Agent automatically handle diagnostics, installation, repairs, and upgrades.