Articles
I Tried Running a Local LLM on a 16GB MacBook Pro for Coding — Here's What Happened
Can a base M4 MacBook Pro with 16GB unified memory run local LLMs for coding? I tested Qwen, LM Studio, and OpenCode to see what works and what fails.
Issue Tracking Is Dead: Rethinking Project Management in the Age of AI
AI is changing how we build software. Here's why I believe traditional issue tracking is broken and what an AI-native project management workflow could look like.
A Month With GLM 5.2: Cheap, Relentless, and Blind
I ran GLM 5.2 as my daily coding agent in OpenCode for a month — full OpenCode Go subscription, wired in as my Hermes agent. It fixed real performance and battery bugs in my macOS app Vitals (CPU ~89% down to ~13%, 143/143 tests passing) for a few dollars a session. But it can't see screenshots, it's a token glutton, and on pay-per-token it burned through $10–20 of Fireworks credits fast. Here's the honest month-long review: what it's great at, where it falls apart, and why at ~$10 nothing else touches it for coding.
Fable 5 Is Back. It Can't Code. It's Never Been More Useful.
Anthropic brought Claude Fable 5 back for global users on July 1 — but it's not allowed to write code, it falls back to Opus 4.8. So I used it as an orchestrator instead, ran Opus 4.8 and Sonnet 5 as sub-agents under it, and shipped fixes across three of my apps in an afternoon. Here's exactly how the orchestrator method works, what it cost, and whether it's worth it.
I'd Never Built a Mac App. So I Built a Whole System Monitor.
One prompt, about 30 hours over two days, two AI models (one got banned mid-build), and a native macOS system monitor I now use instead of Activity Monitor. The full build story — fan-control hacks, a 17.5 GB ghost, and all the bugs in between.
They pulled fable 5
Two days after I wrote a love letter to Claude Fable 5, the US government forced Anthropic to shut it off. Here's what actually happened, why it happened, what it means for developers outside the US, and what Anthropic does next.
Claude Fable 5 Built Two 3D Games From One Prompt — Full Review & Test
I gave Anthropic's Claude Fable 5 (Mythos-class model) one prompt and walked away. It built two full 3D browser games with Three.js. Here's my honest review — what worked, what didn't, and how to try it yourself.
I Deleted Backblaze the Day GitHub Got Breached
How a single tweet on a Tuesday morning made me rip out my cloud backup, throw my external Time Machine drive in a drawer, and rebuild my entire backup pipeline on a TrueNAS box in my closet. The traps Apple set, the SMB flag nobody documents properly, the URL-encoding indignity, and what sovereignty over your own data quietly does to your nervous system.
The Hidden Cron That Ate My Free Tier: Read the Source Before You Use a Package
A cautionary tale about reaching the 91% mark on a serverless free tier and discovering the top function in the breakdown was a maintenance cron from a third-party component I'd never opened the source of. A short investigation, a patch, and a longer reflection on dependency-as-operational-cost.