Guides

Local AI guides

Run local AI on your own hardware - practical, cost-driven guides.

Write a guide
Guide

Musk says Grok's political lean is 'a function of SF Bay Area political views'

Musk says Grok's political lean reflects its trainers' geography. What the admission means for closed models, and why open weights let you set the values.

Aug 29, 2026

Guide

OpenAI ends its Cursor partnership after the SpaceX acquisition

OpenAI confirms it is ending its Cursor partnership after SpaceX acquired the company. Direct model access ends November 12. What developers can do.

Aug 29, 2026

Guide

How AT&T cut AI coding costs 56% with open-weight models and LiteLLM

AT&T routes employee queries to cheap open-weight models via LiteLLM, cutting coding AI costs up to 56% with a 2% quality drop. What it means for you.

Aug 28, 2026

Guide

Nvidia denies pausing its AI cloud commitments initiative

Nvidia denies pausing its AI Cloud Commitments program after a report claimed cloud partners balked at leases restricted to Nvidia-approved customers.

Aug 28, 2026

Guide

AMD ROCm 10: what the launch means for local AI

AMD ships ROCm 10: TheRock builds for Radeon and Instinct, ROCm.AI optimization agents, RX 9050 support, and a unified Windows SDK. What changes for local rigs.

Aug 28, 2026

Guide

512GB of local AI memory: one M5 Ultra box or a four-box cluster?

One Mac Studio M5 Ultra, 4x DGX Spark, or 4x Ryzen AI Halo: three ways to buy 512GB of local LLM memory. Prices, bandwidth math, honest tradeoffs.

Aug 26, 2026

Guide

Agents on Rails: the 16-model leaderboard and what local models can do

Ruby on Rails benchmarked 16 frontier models on 63 real Rails runs. See the leaderboard, the local-vs-hosted story, and which model wins by cost.

Aug 24, 2026

Guide

DGX Spark benchmarks: which local model wins in 2026

The best open-weight models that fit the 128GB DGX Spark plus independent benchmarks - BridgeBench, Exxact, community NVFP4 runs - by tok/s, latency, pass rate.

Aug 19, 2026

Guide

GLM-5.3: the coding upgrade Z.ai is holding back for safety review

Z.ai's GLM-5.3 is a post-training coding upgrade of the 743B GLM base that found 1,097 critical bugs in open source. Open weights are held for safety review.

Aug 14, 2026

Guide

Cloudflare Wallets and x402: agents that pay their own way

Cloudflare Wallets give AI agents stablecoin wallets with spending guardrails, and x402 lets them pay per HTTP request. What it means for agent payments.

Aug 05, 2026

Guide

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

Guide

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