VOL 01 012 BYTES RECORDED WED, AUG 12, 2026

Small bytes of tech, worth chewing on.

Bite-sized reviews and longer takes on the hardware, software, games, and AI worth your time.

03 · More Content
AI
No. 05 · JUN 11, 26

I Built a ServiceNow AI Assistant Instead of Licensing One

Enterprise platforms sell you an AI assistant by the seat. I built one that lives inside the platform, runs on token-billed LLM calls, and lets me decide what it can do.

Read byte
Software
No. 06 · MAY 12, 26

The UK Just Voted to Hand a Cabinet Minister the Off Switch

An amendment to the Children's Wellbeing and Schools Bill gives a single minister the power to block sites, ban VPNs, and ID-check the entire UK adult internet. It cannot stand.

Read byte
Software
No. 07 · MAY 07, 26

How Tailscale Helped Me Ditch My iCloud Storage Subscription

A mesh VPN built on WireGuard that takes ten minutes to set up and turns every device you own into one private network. Why I use it for my home lab, and how to get started.

Read byte
Gaming
No. 08 · MAY 06, 26

A Decent Week at Microsoft Gaming, With Caveats

Xbox Mode shipped, console Copilot got killed, Sharma brought in her bench. The first stretch of Microsoft Gaming news in a long time that did not actively make my Linux post stronger.

Read byte
AI
No. 09 · MAY 04, 26

Getting Started with Local LLMs on a Mac: OpenCode + LM Studio

A practical, opinionated walkthrough for wiring up OpenCode against an LM Studio server on Apple Silicon: installs, model picks for different RAM tiers, and how it actually feels to use day to day.

Read byte
AI
No. 10 · MAY 02, 26

Running LLMs Locally Is Quietly Becoming the Better Option for Home Devs

Coding harnesses like OpenCode and pi.dev, paired with LM Studio and a good open model, now cover most of what home developers actually use cloud AI for, and the cost trajectory of frontier APIs is making that more true every quarter.

Read byte