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
Table of Contents Introduction Environment Requirements Core Features Core Design and Code Analysis Actual Execution Demo Architecture Overview How You Can Expand Future Plans & Conclusion What is this It is a basic debugger, running on Linux and implemented in C++, aiming to create a debugger that is easy to read and expand. In addition, Lavender's main function is to help users analyze the logic
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
You're in another app and there's a timer counting down at the top of your phone. You lock the screen and the same timer is sitting there. You swipe down to the Notification Center and it's there too, still ticking. It looks like a notification, but a notification can't tick. That's a Live Activity. It looks like three different surfaces (Dynamic Island, lock-screen banner, Notification Center ent
I finished an English series on the way I think ordinary people can start using AI for real work. The point is not to become an AI expert first. The point is to have one place where you can say what you want, give the tool access to the right folder, and check the result. Anything important still needs a human pause: publishing, deleting, paying, or authorizing. My preferred starting point is simp
In the previous post, I walked through the compensation logic in each service. The code looks clean on paper. But sagas have a lot of moving parts, and bugs tend to hide in the transitions between services, not inside a single service. This post covers how I test the saga system: unit tests for each service, orchestrator routing tests, and the edge cases that caught me off guard. The orchestrator'