Nick's banner
Nick's profile picture

Nick

@nickbaumann_15,748 subscribers

codex @openAI | prev @cline | product of @UWMadison 🦡

Shorts

GPT-5.4 mini matters for subagents because it changes what feels worth handing off. The parent thread should hold the architecture, plan, and progress narrative. Fast subagents can explore the repo, check hypotheses, and preserve the parent thread’s limited attention.

GPT-5.4 mini matters for subagents because it changes what feels worth handing off. The parent thread should hold the architecture, plan, and progress narrative. Fast subagents can explore the repo, check hypotheses, and preserve the parent thread’s limited attention.

99,512 次观看

Just created a .clinerules protocol that makes building custom MCP plugins with Cline ridiculously easy. Drop this file in your project and Cline guides you through the entire process -- planning, implementation, and testing. MCP is how AI agents will connect with our digital world. Start building now while everyone else is still figuring out what MCP even is. I'll drop the file below 👇

Just created a .clinerules protocol that makes building custom MCP plugins with Cline ridiculously easy. Drop this file in your project and Cline guides you through the entire process -- planning, implementation, and testing. MCP is how AI agents will connect with our digital world. Start building now while everyone else is still figuring out what MCP even is. I'll drop the file below 👇

70,255 次观看

in a similar vein to Kieran Klaassen & Every 📧 's "compound engineering", I've used a prompt every day for the past few months called "self-improving Cline" (linked below). at the end of the task, it evaluates any rule I had turned on and proposes updates based on any friction points during the task. now, all my clinerules are extremely refined and improving every time I use them.

in a similar vein to Kieran Klaassen & Every 📧 's "compound engineering", I've used a prompt every day for the past few months called "self-improving Cline" (linked below). at the end of the task, it evaluates any rule I had turned on and proposes updates based on any friction points during the task. now, all my clinerules are extremely refined and improving every time I use them.

42,726 次观看

Videos

没有更多内容可加载