Building a Three-Stock Ticker with ESP32 and M5Stack Core2

Engineering a responsive, secure stock ticker with an ESP32, M5Stack Core2, PlatformIO, FreeRTOS, and Alpha Vantage A small stock ticker is a useful embedded-systems exercise because it crosses several boundaries at once. The device must join Wi-Fi, establish a trusted TLS connection, parse remote JSON, transform time-series

The 32 KB Ceiling

How adding tags to my metrics silently killed two bitcoin miners' telemetry reporting for nine days. I run two NerdAxeGamma (BM1370) bitcoin miners that push telemetry into InfluxDB 2. It worked fine for months. Then one morning the miners started logging this: ₿ (132501) InfluxDB: HTTP POST Status = 200, content_

Building TokenMonitor: A Native macOS Menu-Bar App for Watching Claude Code Eat Tokens

How a weekend itch turned into a notarized, cyberpunk-styled menu-bar app — and what I learned about undocumented OAuth endpoints, JSONL transcript spelunking, and the dark corners of NSPanel. Why If you use Claude Code a lot, you live with three nagging questions: 1. How close am I to

Inventory Blindness: Why AI Agents Forget the Skills They Already Have

There's a hard problem hiding inside every serious agent deployment: how do you give an agent access to all the capabilities it needs without burning the context window just to list them? I recently came across a discussion that reframed this problem in a way I found genuinely

Shoot, Frame, Done: In-App Camera Capture in PictureFramer 1.4

Until now, digitizing a framed painting with PictureFramer meant a three-app dance: open Camera, shoot the picture, switch to Photos to check it, then open PictureFramer and re-find the shot in the picker. Version 1.4.0 collapses that into one flow: tap Take Photo inside the app,

Why I Switched from Oh My Posh to Starship (And What My Config Looks Like)

I switched my shell prompt from Oh My Posh to Starship after years of using Oh My Posh, and after a day of using it, I don't see myself going back. The two projects solve the same problem — a fast, informative, cross-shell prompt, but they approach it

PictureFramer is on the App Store

A museum-photo straightener built on Vision and Core Image, with optional bring-your-own-key reflection removal — free, iOS 17+, no data collected. Download on the App Store · pictureframer.corti.com PictureFramer solves one narrow problem properly: you photograph a framed painting in a museum, you can never stand

Review Your AI's Code Before It Ever Hits GitHub: tuicr + gh-dash + Claude Code / Copilot CLI

AI coding agents have changed who writes most of the code in my PRs — but they haven't changed who is accountablefor it. The weakest point in an agent-driven workflow is the moment between "the agent says it's done" and "I open a

Your Prompts Are Technical Debt: Why Scaffolding Built for Older Models Hinders Newer Ones

When Anthropic shipped Claude Opus 5 on July 24, 2026, the team at Every — a publication that runs much of its editorial and engineering operation on Claude-based agents — spent a week testing it before publishing their verdict. The title of their review, "Vibe Check: Claude Opus 5 Is

Monitoring Multiple Docker Hosts with Dozzle — the Easy Way

If you run Docker on more than one machine, you know the drill: something misbehaves, and you start SSH-hopping between hosts, running docker ps and docker logs -f until you find the culprit. It works, but it doesn't scale — and it's miserable at 2 a.

Reaching Your Home Lab from Anywhere with Self-Hosted NetBird, and the Four Problems You'll Actually Hit

Self-hosting a mesh VPN sounds like a weekend project, and the happy path mostly is. What the quickstart guides don't tell you is what breaks after the dashboard comes up. I recently deployed NetBird on my own infrastructure to reach my home lab from anywhere, and hit

Teaching My iPhone App to See Through Museum Glass

My little iOS app PictureFramer does one thing: you photograph a framed painting in a museum, and it straightens the photo — finds the frame, fixes the perspective, keeps a clean strip of wall around it. Pure on-device geometry, no network, done. Then I looked at my camera roll. Half

ZoomIt4Mac 1.1.0: Record a Region, Copy Text from Anywhere, and Never Update Manually Again

ZoomIt4Mac — the native macOS re-implementation of the Sysinternals ZoomIt presentation tool — just got its first big update since launch. Version 1.1.0 brings four new features, and one of them means you'll never have to download an update yourself again. Download ZoomIt4Mac Here's what&

ZoomIt4Mac: Bringing the Sysinternals ZoomIt Experience to macOS

If you have ever watched a great technical presenter on Windows, you have probably seen ZoomIt in action — Mark Russinovich's tiny Sysinternals tool that zooms into the screen, draws arrows over live demos, and runs break timers, all without ever showing a window. When I present on a

Cleaning Up the Adobe Mess: Orphaned Office Add-ins After Uninstalling Acrobat Reader on macOS

Adobe and I have history. A while back, I wanted to cancel my Photoshop suite subscription and got hit with a penalty fee for "canceling outside of the cancellation window" — a fee for the privilege of no longer being a customer. Lesson learned, I thought. Apparently not. Recently

PictureFramer: Straightening Museum Photos with Vision, Core Image, and One Carefully Placed Y-Flip

I take a lot of photos of paintings in museums. They all have the same problem: you can rarely stand dead center in front of the artwork, so every photo is a little rotated and keystoned, with the frame converging toward one side. Cropping doesn't fix perspective, and

Claude Code's /goal: Set a Condition, Walk Away. A practical guide

Claude Code has always been turn-based: you prompt, Claude works, control returns to you. That model breaks down for long-running work — migrations, backlog grinding, "keep fixing until CI is green" — where you end up typing "continue" every few minutes. The /goal command, introduced in

Loops, Not Tasks: How GPT-5.6 Turns Collaboration with AI into a System

GPT-5.6 heralds a new way of collaborating with AI. Instead of using AI to complete one task at a time, you build a system that scans the available information, turns it into proposed decisions, and carries out the ones you approve. Over time, the system compounds your feedback

Inside the J-Space: Anthropic Finds a "Global Workspace" in Claude

A technical look at the July 2026 interpretability paper "Verbalizable Representations Form a Global Workspace in Language Models" — what was actually measured, what it means, and where healthy skepticism belongs. On July 6, 2026, Anthropic's interpretability team (Gurnee, Sofroniew, Lindsey et al.) published a paper on

Turning Supacode Into a Full IDE: Flexible Panes for Agents, Editor, File Management and Git, all using VIM Keybindings

I've spent the last while collapsing my development environment into a single window. Not VS Code, not a raw Ghostty grid held together with a tmux config but Supacode. What started as "a nicer harness for running Claude Code, OpenCode or Copilot CLI in parallel" has

Teaching an LLM to Speak Vestaboard Note: Building Vestaboard AI

A Vestaboard is a split-flap display — the kind that used to clatter through train-station departure boards — reimagined as a connected home object. It's gorgeous, it's tactile, and it has a wonderfully small canvas: 3 lines of 15 characters, so 45 characters of real content,

From Tokenmaxxing to Token Discipline: The 2026 Reckoning in AI-Assisted Engineering

For a brief window in early 2026, the loudest signal of "AI adoption" inside large tech companies was a number going up: tokens consumed. Six months later, the same number is something finance teams are actively trying to drive down. This is a post about that reversal — what

AI assisted Software Engineering: Scaffolding Your Way from One Agent to a Team

How agent-teams-scaffold turns any repository into a launchpad for Claude Code Agent Teams — and why that's the cleanest jump from Level 6 to Level 7 of AI adoption. The wall between "an agent" and "a team of agents" If you've

Serving TokenTelemetry, a localhost-only app on the internet, safely using just a script: a tour of tokentelemetry-caddy

I host OpenClaw and Hermes on two different virtual machines in the cloud. I want to be able to view their token usage using TokenTelemetry, but the tool is built to run unauthenticated on localhost. To get a way to securely publish the TokenTelemetry endpoint of http://localhost:3000 to

Connecting OpenCode to a Self-Hosted LLM (vLLM + Nemotron 3 Super)

Coding agents like Claude Code and Codex are excellent, but both are wired to a specific vendor's API. If you run your own inference stack — for cost control, data residency, or because you have GPUs sitting idle — you want an agent you can point at your endpoint. OpenCode