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
Blog
All Posts →
Intelligence Is Starting to Be About Wealth
Fable 5 ran a 15-hour task for $420. After June 22 it leaves Coding Plan for API rates, a 10x cost jump: access to top intelligence is a wealth problem.
3 min read
Claude 4.8 Let Me Down, But It’s Not Just Claude’s Problem
Claude Opus 4.8 kept failing my research and engineering tasks, so I moved them to GPT 5.5. Top models rotate—NVIDIA, AMD, and Zhipu prove survival wins.
8 min read
Projects
Personal projects and works →
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 AILLM InferenceOpenAI API
AIMA AMD395 Qwen3.6 35B Linux Engine — Native Inference Engine
Native BF16 engine for Qwen3.6-35B-A3B on AMD Ryzen AI Max+ 395. No Python/PyTorch/vLLM/system ROCm. 262K ctx, OpenAI API, SSE streaming, function calling.
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.