Claude Code - Using Context More Efficiently
A Stop hook that warns when a session's context gets too long, and a one-paragraph skill for handing off work that hasn't started yet.
Paul’s Programming Notes
Latest posts
JavaScript roguelike development in 2026
rot.js covers the algorithms and Phaser the rendering, but no JavaScript library handles turn-based combat, inventory or progression. I wrote those myself.
Kimi K3’s cache discount doesn’t survive OpenRouter
Moonshot caches prompts automatically, but the discount never reaches you through OpenRouter. Backing the real rate out of the billing rows.
Every LLM tool call re-sends your entire conversation
Every tool call POSTs the whole conversation back to the API, so one prompt can bill many times its context window. Prompt caching cuts reads to ~10%.
Home Assistant Leak Notification Automation
The Sonoff SNZB-05P seems like the best Zigbee leak sensor right now. It’s around $20, and its snap-on WLDC200 sensing cable detects water anywhere along the cord, so it isn’t just watching a single spot the water can spread around. I have them in appliance drip pans and under sinks, all feeding one Home Assistant automation that alerts my phone when a sensor trips and sends an all-clear when it…
Is CloudNativePG ready to replace Aurora or AlloyDB?
CloudNativePG is a Kubernetes operator for running PostgreSQL. It joined the CNCF Sandbox in January 2025, applied for Incubation and added PostgreSQL 18 support later that year, and shipped v1.30 in June 2026. It’s used by some big companies like IBM, Google Cloud, and Microsoft Azure, and it looks solid, though I haven’t run it myself. I’ve been weighing whether it’s worth advocating a swap from…
Switching my local LLM to Qwen 3.6, a 35B Mixture-of-Experts model, on a 16 GB GPU
Qwen3.6-35B-A3B fits on a 16 GB card with llama.cpp's `--n-cpu-moe`. Disabling thinking mode needed both reasoning-budget 0 and enable_thinking=false.
The best-value thin clients with a PCIe slot in 2026
I was picking hardware for an OPNsense router and needed a real PCIe slot, which most cheap low-power boxes don’t have. A slot lets you add a network card with SFP+ or more ports, and swap it later for something else (like a GPU).
A dead man’s switch for a single-host monitoring stack
If Prometheus and Alertmanager run on one box, nothing alerts when that box dies. A `vector(1)` watchdog routed off-host turns silence into the failure signal.
Replacing my Raspberry Pis with used thin clients
A used Dell Wyse 5070 at $43 and an OptiPlex 3000 at $84 beat a Pi 5 on price for closet servers. Benchmarks, the memtest warning, and the M.2 fit problems.