Three Green Lies: Debugging a Self-Hosted LLM Observability Dashboard
Within a week of standing up the dashboard, three panels were showing bad data. None of them was a Grafana bug. I…
-
-
How I Drive WordPress From Claude Code (REST, Playwright, wp-cli)
Driving WordPress from Claude Code (Anthropic’s terminal coding agent) fights the platform’s core assumption roughly every other operation. WordPress was built for…
-
Sorting a Filesystem Hoard With Local LLMs: What 2,300 Files Told Me About My Obsidian Vault
What do 2,300 random files on a knowledge worker’s laptop actually look like? I let a local LLM tell me. TL;DR I…
-
Anti-detect browser benchmark 2026: 7 stealth tools, 31 Cloudflare targets, 651 verdicts
I built a scraper. Cloudflare killed it in 48 hours. I built a web scraper for Canadian small-cap stock data and Cloudflare…
-
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive → DFlash → MTP for Qwen3.6-27B
TL;DR MTP wins on wall clock above output ~900 tokens. Below that, plain autoregressive is faster. The DFlash Decode Collapse. DFlash decode…
-
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
I pulled a Quadro M4000 out of a used Dell Precision T5820, dropped in an RTX 3090 Ti, and turned the box…
-
The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.
That afternoon a Slack bot told me a script had NEVER RUN. That was a lie. The script had pulled 81 weather…
-
Stop Claude Code from Lobotomizing Itself Mid-Task
Claude Code has a feature called auto-compact that quietly destroys your session quality. The Problem I was three hours into a multi-file…
-
How I Track Claude, Codex, and Gemini Quotas from One Script
Updated May 30: added what I learned wiring these three together, plus the budget thresholds that now trigger automation. (If you’re trying…
-
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
Inference arbitrage means routing each AI task to the cheapest model that can handle it at acceptable quality, instead of sending everything…
