April 16, 2026· ~7 min readCoreCoder: Claude Code's Architecture in 950 Lines of Python Claude Code is roughly 512,000 lines of TypeScript spread across a closed repository. CoreCoder, built by Yufeng He over two days, distils that into
April 15, 2026· ~8 min readRunning Gemma 4 on a Raspberry Pi 5 with the Hailo-8: What Actually Works You cannot run Gemma 4 on a Hailo-8. That is not a headline designed to disappoint you; it is simply a hardware fact. The Hailo-8 has 18 megabytes of
April 13, 2026· ~8 min readArcee AI Trinity-Large-Thinking: The $20M Open Model Chasing Claude Twenty-six people. Twenty million dollars. One model that outperforms GPT-5 on reasoning benchmarks. Arcee AI's Trinity-Large-Thinking isn't suppose
April 13, 2026· ~7 min readvLLM vs SGLang: Choosing an LLM Inference Framework in 2026 Serving large language models at production scale boils down to one problem: getting the most tokens out of your GPU per second, per dollar. Two open
April 4, 2026· ~7 min readGemma 4: Google DeepMind's Most Intelligent Open Models On April 2, 2026, Google DeepMind released Gemma 4 — the fourth generation of its open model family, licensed under Apache 2.0. Built on research and
March 20, 2026· ~3 min readUnified LLM Power: Integrating Public and Private APIs with LiteLLM for GraphWiz.AI ## Executive Summary **Challenge:** The architecture lacks centralized LLM integration, creating fragmented API access, inconsistent observability,