One thread. Multiple AIs. Deliberation, not polling. Most people use AI like this: 🤦 Ask one model → get one answer Ask multiple models → compare results That’s not thinking. That’s polling. Not side by side. Not isolated. But in sequence — where each one reads what the previous one said before responding. Manual Council is the simplest form of that idea. No backend. No orchestration. No
I recently had a requirement where, if a user opens the app in multiple browser tabs, only one tab can be active at a time, and the rest are locked. Here are the core requirements as I see them: Uniquely identify each tabs Store the active tab somewhere If a user opens a new tab, lock it if there is already an active tab If the active tab is closed, detect that and inform the other tabs Sounds sim
I spent long hours debugging why Google couldn't index my React app. Lighthouse showed green scores. The app felt fast. But Search Console kept flagging LCP failures and CLS shifts I couldn't reproduce locally. The fix? Four lines of metadata and one misunderstood render strategy. If you've ever shipped a "fast" SPA and watched it flatline in search rankings, this Core Web Vitals SEO guide is for
I wanted to add live chat to my WordPress sites without loading a 500KB third-party script. So I built my own. GhostChat is an open source embeddable Widget: Vanilla JS, no framework, ~10KB Backend: Cloudflare Workers + Durable Objects for persistent WebSocket connections Payments: Stripe for the hosted tier Self-hostable: Bring your own Cloudflare account Durable Objects give you stateful serve
Comments
Updated May 2026: Now covers virtual desktop (Spaces) restoration and iCloud sync across multiple Macs, both shipped in ShiftPlus 1.3. TL;DR A complete macOS workspace includes apps, window layouts, browser profiles, virtual desktops, and terminal state. Native macOS saves almost none of it. Most third-party tools cover one slice: Stay and Spencer handle window layouts, Shift handles browser profi
In July 2025, a developer's Claude Code instance hit a recursion loop and burned through 1.67 billion tokens in 5 hours, generating an estimated $16,000 to $50,000 in API charges before anyone noticed. The agent did not crash. It did not throw an error. It just kept calling tools, getting confused, calling more tools, and silently accumulating cost. Old software crashes. LLM agents spend. This is