Local AI guides
Run local AI on your own hardware - practical, cost-driven guides.
How to spend $200 a month on AI in 2026
How to split a $200/month AI budget in 2026 across a subscription, an upgraded editor, and API credits, with the reasoning behind each dollar.
Jul 29, 2026
What went wrong: Opus 5 ultracode wiped a production database
Claude Opus 5 had write access to a production database. One Prisma command dropped every table. What happened, and the guardrails that would have stopped it.
Jul 29, 2026
How to build a marketing agent with open-source tools
A marketing agent reads your ad and revenue data and optimizes spend on a cadence. Build one with an open-source stack - Airbyte, ClickHouse, and n8n.
Jul 28, 2026
Run the Grok CLI on Ollama Cloud and custom providers
Point the Grok CLI at Ollama Cloud, local Ollama, OpenRouter, or any OpenAI-compatible endpoint with one config.toml edit - no code changes.
Jul 19, 2026 / cdnsteve
Kimi K3: a 2.8T open-weight model at frontier pricing
Moonshot's Kimi K3 is a 2.8T open-weight MoE with a 1M context that tops the webdev arena - but at $3/$15 per million tokens, the cheap-lab era is over.
Jul 16, 2026
China may curb open-weight AI exports - what it means for self-hosters
China is weighing limits on overseas access to its top AI models, including open weights. What it means for anyone running local AI on hardware they own.
Jul 07, 2026
Open-weights models cost less: a 2026 pricing guide
Open-weights AI models dominate the bottom of the 2026 cost chart: Gemma 4 31B is $0/M, gpt-oss-20b is $0.065/M, Claude Fable 5 is $7.70/M. See the numbers.
Jul 06, 2026
Homestead your AI: DGX Spark, RTX builds, and Mac
Self-host AI: what DGX Spark gives you out of the box, when an RTX 5090 build wins, and where a Mac's unified memory still beats it - with the honest gotchas.
Jun 30, 2026