Blog

Latest Posts

Thoughts on engineering, testing, and building reliable systems.

August 7, 2026
AILocal LLMDeepSeekOpen SourceSwiftUI

DwarfStarLauncher: a GUI for DS4, built with the model it serves

I wrote a native SwiftUI launcher for ds4, using DeepSeek V4 Flash served by ds4 as my coding assistant. No cloud APIs for inference.

→
August 5, 2026
AILocal LLMDeepSeekOpen SourceHardware

DeepSeek V4 Flash 0731: Exciting news for the local AI community

DeepSeek V4 Flash landed in late April; the 0731 checkpoint was shipped on July 31. The release comes with native MXFP4 weights, and it's a good model for its size that runs on 'consumer' level hardware — with the 2026 RAM price crisis as the caveat.

→
July 10, 2026
AILocal LLMOllamaApple SiliconMLXOpen Source

How Apple Silicon + MLX Became a Great Platform for Local AI

Ollama's MLX engine, multi-token prediction, and NVFP4 quantization are making local AI noticeably faster and better

→
July 4, 2026
TestingProperty-Based TestingPythonTypeScriptAI AgentsSoftware Quality

Property-Based Testing: Write Fewer Tests, Find More Bugs

Property-based testing replaces hundreds of hand-written test cases with a few lines of code and finds more bugs. It's also a natural fit for the age of AI agents.

→
January 20, 2026
AILocal LLMDeepSeekOpen SourceHardware

Running 284B AI Models on Your Own Hardware: The DS4 Project and Local Inference

How antirez's DwarfStar engine, DeepSeek V4 Flash's MoE architecture, and aggressive quantization are making frontier-level AI accessible outside the cloud — and what it means for developers who care about privacy, cost, and control.

→
January 15, 2026
CI/CDTestingAIEngineering

CI in the Age of AI Agents

How AI coding assistants are changing the way teams write, maintain, and think about CI pipelines and automated tests.

→