₿ Yan Luiz

Failed Offboarding 250 USD spent in 2.5 years. The W3F was absolutely right to step in and end the madness. BUT: People were treated badly in the process. Those that tried to make an honest effort and help the eco. There were no exit interviews to thank ecosystem agents and teams for their service. At least that I’m aware of. They were all just told that the relationship is ending. It’s a bad way to end a working relationship that causes a lot of grief and sadness in those that believed in the mission. You have to ask: What society do you want to build? How do we relate and treat each other, even when relationships are ending? If you treat mercenaries and missionaries all the same, there is no reason to be a missionary. A Cypherpunk Utopia cannot be built on autism alone.

🚨 BREAKING: Someone built the one tool every AI coder was silently begging for. It's called CodexBar — a tiny macOS menu bar app that tracks your AI usage limits in real-time. No more "why did my Claude Code stop working?" No more logging into dashboards. No more guessing when your limits reset. Here's how it works: → Lives in your menu bar — always visible, zero distraction → Shows session + weekly usage for every AI coding tool you use → Countdown timer tells you exactly when your limits reset → Tracks Codex, Claude Code, Cursor, Gemini, Copilot, Kiro, and more → One icon per provider or merge them all into one Here's the wildest part: It reads your local data. No passwords stored. No cloud sync. No login required. Pure on-device privacy. It even has a built-in CLI so you can check usage from your terminal or CI pipelines. Install in one command: brew install --cask steipete/tap/codexbar 1.7K GitHub stars. 1,177 commits. 28 contributors. Actively maintained. 100% Open Source. MIT License.

An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently. When the agent is confused it runs git-blame and messages the right engineers in Slack. By Monday the agents finished the plugin feature. That's one example of how the best engineers are shipping software right now. Developers will soon orchestrate 50 AI agents in parallel and the difference between a good engineer & a great one would come down to specs. You can't write a spec that holds up at that scale without genuinely understanding what you're building at a deeper level. The next-gen developer who understands the fundamentals, can architect well and orchestrate agent is going to be a 1000x developer!

someone vibe coded a 3d city where every github developer is a building more commits = taller building. more repos = wider base. lit windows = recent activity

someone vibe coded a 3d city where every github developer is a building more commits = taller building. more repos = wider base. lit windows = recent activity