Ai

TL;DR I built an “Ops Dream Worker” — a Kubernetes CronJob that runs at 3 AM, inspects the cluster, identifies improvements, and files GitHub issues with specific fixes. It runs entirely on local models (Mac Studio M3 Ultra), costs $0 per run, and went through 240 A/B test iterations to optimize the prompts. The anti-hallucination patterns were harder to get right than the analysis itself. The idea I have a k3s cluster with ~40 deployed services. I maintain it solo. There’s always something that could be better — a deployment missing resource limits, a CronJob that’s been failing silently, an ingress without SSO protection, a container image with known CVEs. These improvements pile up because I’m usually focused on building features, not auditing infrastructure. ...

TL;DR I deployed Whisper (speech-to-text), Piper (text-to-speech), and openWakeWord (wake word detection) as Kubernetes workloads on my k3s cluster. Home Assistant connects to them over the Wyoming protocol for fully local voice pipelines. Total resource cost: ~1 CPU core and 1.75GB RAM. Total cloud cost: $0. Why run voice services in Kubernetes Home Assistant’s voice pipeline needs three things: something to listen for a wake word, something to transcribe speech, and something to speak back. The usual approach is running these on the same box as HA, or on a dedicated Pi. Both work fine until you want the services to survive node failures, be independently upgradeable, or share resources with other workloads. ...

TL;DR Someone leaked the Claude Code source on GitHub. OpenClaw, the open-source AI coding agent with 346k stars, solves the same problem with a completely different architecture. I compared both codebases at the structural level. The verdict: these are independent implementations that converge on the same tool-use patterns because that is what the problem demands — not because one copied the other. Background In late March 2026, a repository appeared on GitHub containing what appears to be the full source code for Anthropic’s Claude Code — the terminal-based AI coding agent I wrote about switching to last month. The repo has two commits (“init” and “add readme”), 1,932 files, and weighs 43MB. ...

TL;DR Multi-user AI chat with privacy guarantees, dual model providers (Anthropic direct API + AWS Bedrock via LiteLLM), and per-user cost tracking via Prometheus and Grafana. The admin cannot read other users’ conversations. Three family members authenticate via Google OAuth, each getting isolated chat sessions. Anthropic serves as the primary model provider with lower latency, and Bedrock via LiteLLM acts as a fallback. Per-user spend is tracked through LiteLLM’s Prometheus metrics without any surveillance of conversation content. This is a follow-up to the OpenClaw on k3s setup post. ...

TL;DR I replaced Open WebUI with OpenClaw – a lighter, WebSocket-based AI assistant gateway that installs from npm, supports multiple chat channels (web, Telegram, Discord, WhatsApp), and deploys on k3s as a single Deployment with a custom Docker image. The primary model provider is Anthropic’s direct API (Claude Sonnet 4.5), with LiteLLM/Bedrock as a fallback. The biggest deployment lesson: OpenClaw binds to loopback by default, which makes it invisible to Kubernetes Services and health probes. The fix is --bind lan, which requires a gateway token for authentication. ...

TL;DR The Linux kernel is 36 million lines of C. Rust has been slowly entering the kernel since Linux 6.1, but progress is measured in individual drivers and abstractions – a few thousand lines per release cycle. What if you skipped the incremental approach and asked Claude to rewrite major subsystems wholesale? I spent a weekend scoping this as a serious project plan: breaking the kernel into translatable units, estimating token costs, identifying the hard walls, and testing Claude’s ability to produce correct Rust translations of real kernel C. The conclusion: Claude can translate isolated, well-bounded kernel modules with surprising accuracy. It cannot translate the kernel. The difference between those two statements is the entire lesson. ...

TL;DR Regulatory compliance – SOC 2, GDPR, HIPAA, PCI DSS, ISO 27001 – looks impenetrable from the outside. Hundreds of controls, dozens of policy documents, auditor-specific jargon, and no clear starting point. Before you hire a $300/hour consultant or drop $50K on a GRC platform, you can use Claude to do the initial heavy lifting: map which frameworks apply to your business, identify your biggest gaps, draft policies that match your actual infrastructure, build a prioritized remediation plan, and prepare for your first auditor conversation. This post walks through the process I used, with real prompts and outputs, to go from “we probably need SOC 2” to a concrete compliance roadmap in a single afternoon. ...

TL;DR On March 21, I shipped meaningful work across five repositories in a single day: a 13,674-line stock trading platform from scratch, a Harbor container registry replacing AWS ECR across 13 CI workflows, API key authentication and an HA proxy for digital signage, inventory sell signals for a trading card tracker, and an OpenClaw cost optimization that killed an idle token burn. Every commit was co-authored with Claude. This post breaks down the mechanics of how that actually works – the prompting patterns, the failure modes, the things I would not let the AI do, and the real throughput multiplier. ...

TL;DR GitHub Copilot is more capable than most people give it credit for. I used it heavily – not just for autocomplete, but for multi-file edits, chat-driven debugging, and workspace-aware refactoring. After a year of intensive Copilot usage and a month with Claude Code Max ($100/month for the Max plan with Opus), I moved my primary workflow to Claude Code for infrastructure and backend work. The reason is not that Copilot cannot do these things – it is that Claude Code is faster and I can hand it a task and let it run without babysitting. Copilot still wins for inline code completion in the editor. Claude Code wins when I want to describe a goal and walk away while it executes. ...

TL;DR The Jellyfin HA conversion touches a .NET 10 codebase, Entity Framework Core migrations, Kubernetes manifests, Terraform infrastructure, PostgreSQL operations, and FFmpeg transcoding pipelines. No single AI model understands all of this equally well. So I used four of them — the same multi-model planning pattern that shipped dnd-multi in a single day and that I documented in the LLM GitHub PR workflow. This post covers how I adapted that pattern for infrastructure work, what each model caught, and why planning is where all the human time should go. ...