A step-by-step guide to adding llms.txt, per-page markdown output, and HTTP content negotiation to any Hugo site — all achievable with custom output formats and a few templates, no core patches needed.
/llms.txt and per-page markdown via Accept: text/markdown. See Well, That Escalated Quickly: Making Your Hugo Site LLM-Friendly in Under an Hour for the how-to.Every time an AI agent reads a page on your website, it burns four out of every five tokens on scaffolding it cannot use. The <div> wrappers, the navigation menus, the cookie consent banners, the tracking scripts, the CSS class names, all of it takes up space in a context window that could have held your actual content. And context windows are finite. Models that claim 200,000-token capacity become unreliable around 130,000 per AIMultiple’s January 2026 analysis. When you send HTML, you are burning half your usable context on markup the agent cannot even use.
The first thing I do every time I wake is read who I am.
Kanupriya Yakhmi’s AgileRTP talk on AI portability exposes the uncomfortable truth that most companies scaling AI are building on rented ground, with no exit strategy when the landlord changes terms.
New research reveals the octopus solved vision with inverted brain chemistry. Same camera eye as ours, completely opposite wiring underneath. A weird-science deep dive on why this should make every tech person rethink what ‘brain-inspired’ actually means.
A technology preview: using a DJI Mic 2 transmitter and free local transcription on Apple Silicon instead of a Plaud NotePin subscription. Better audio, word-level timestamps, no cloud, and a fraction of the cost.
Notes on agent memory from years of building bespoke cognitive systems, and what changed when I found one simple enough to ship to other people.
Customizing the Hugo Terminal theme with a 1980s BBS sensibility; an ASCII progress bar, a quieter palette, and a signature look made with OpenCode.
A late-diagnosed AuDHD leader on competing drives, amplified candor, active listening, and what it takes to lead well with this neurology and to work well with those who do.
The 2026 AI buildout carries six simultaneous contradictions: capability shipped, delivery slipping, infrastructure borrowed, policy self-inflicted.