On an M4 Mac mini (Codex 0.150.1), stdio MCP servers keep the controlling terminal, so a child reading the tty SIGTTIN-stops the CLI. Shell tools got setsid; MCP didn't.
Khala open-source song generator needs 24GB+ NVIDIA VRAM, ~52GB weights, and still carries a 2026-05-07 quality warning. Notes on the 64-layer RVQ pipeline and generate API.
Notes on a DEV Community article that wires up FastAPI as an OpenAI-compatible RAG API layer with llama.cpp, Chroma, and Open WebUI, plus where the architecture fits and what to watch for.
The fix for CVE-2024-41110 missed the upper bound — request bodies over 1MB bypass AuthZ plugins. All Docker Engine versions before 29.3.1 are affected.
From Docker hell to Lite + LLM correction. A retrospective on my own experimentation, plus an introduction to someone else's browser-based NDLOCR-Lite implementation.
A roundup of four topics around AI agent development and operations in February: a study showing AGENTS.md may be counterproductive, Continue.dev's CI-integrated AI checks, AWS Strands Agents' built-in session persistence, and Docker Shell Sandbox for isolated agent execution.
Japanese text gets mangled when inserting into MySQL on Docker from PowerShell. PHP-based insertion works fine, suggesting the issue is PowerShell's character encoding, not the application.
A plan to build an internal help desk RAG system using a Mac mini M4 Pro and Dify. Highlights what's new in Dify circa 2025 and tips for running local LLMs.
From browser OCR and server-side OCR to cloud APIs and AI — a roundup of what I learned trying to implement Japanese OCR on the web, including the limits of each approach.
