Stealth Models
7 minStealth AI models hide behind generic branding, vague claims, and selective demos, which makes evaluation much harder than it should be.
Essays tagged Development by Jonathan R. Reed.
This archive groups writing by theme. Posts tagged Development include build notes, security lessons, design tradeoffs, and experiments that connect software decisions to real deployment constraints.
Use this page as a focused reading path through the site. The articles below are ordered newest first and link back into adjacent topics so you can move from a narrow subject into related AI, security, design, tooling, ethics, and development notes without relying on search alone.
Smaller tag archives are kept because they capture useful side threads across the work. Even when a tag only has a few posts, it gives readers a stable entry point into the ideas, references, and projects that shaped that part of the site.
The goal is not to turn every tag into a broad category page. It is to make the archive useful for people who arrive from search, a shared link, or an old project note and need enough context to know why the topic mattered here clearly before they keep reading.
Stealth AI models hide behind generic branding, vague claims, and selective demos, which makes evaluation much harder than it should be.
The paper clip was not inevitable. The Gem won because its geometry gripped well, damaged paper less, and scaled cleanly in manufacturing.
Ten strange Apple patents, from pizza boxes to shape-shifting mice, and what they reveal about experimentation inside consumer hardware design.
Ray Clicker is an idle game living inside a productivity tool. Notes on Raycast UI limits, save migrations, and optimizing for fun over balance.
Animating the Hello.World Consulting logo in Manim: a spiky SVG, hours of debugging, a ten-minute rebuild, and why motion in code beats AI video.
One contact form, 28 commits, and a Cloudflare env var typo. What it actually takes to send email from a personal site.