A 1M-token LLM context window is a tool, not a target. How context actually works, why long threads cost more on every turn, and when to start a fresh chat versus keep going, with practical Claude Code tips and /context.
A file-based pattern for coordinating multiple LLM agents on one task: a single shared, per-feature STATUS.md the agents read and write under explicit rules, how to make them follow a protocol and survive context loss, and when not to use it.
The hidden cost behind AI-assisted coding: the GPUs, power, and data-center infrastructure that make it work, whether current pricing reflects real demand, why providers lose money at scale, and what that means for you.
Building a homelab SSH jumphost that lets you pick any server from a fuzzy-finder (fzf) menu by friendly name instead of memorizing IPs, including the select-host script, autoload on login, and SSH key management.
What passkeys are and why they are more secure and convenient than passwords: how the public-key authentication works, its security and usability advantages, and a quick guide to start using passkeys on iPhone and Mac.
Why software bills of materials (SBOMs) matter for security teams, managers, and developers, how to win management buy-in, and a short hands-on demo generating an SBOM in a GitLab CI pipeline.
A practical experiment in using a to-do list to run work and home life: why offloading tasks from your brain works, how I categorize them, the pitfalls to avoid, and which app to pick.