**The Double-Edged Sword of AI: Why Garry Tan's Claude Code Setup is Causing a Stir** Garry Tan, the CEO of Y Combinator, has been making waves in the tech world with his enthusiasm for AI agents. At a recent SXSW audience, he confessed to "cyber psychosis," a condition that has left him barely sleeping. Tan's excitement stems from his work with Claude Code, an AI tool that has garnered significant attention. Tan's setup, which he generously shared on GitHub, includes six "opinionated" skills that instruct the AI on specific tasks. These skills are essentially reusable prompts that enable the AI to behave in various roles or tasks. Tan's enthusiasm is understandable, considering the potential of AI to revolutionize the way we work. He's so excited that he's been working tirelessly, often going without sleep. Tan's "gstack" setup has been met with both praise and criticism. On one hand, his willingness to share his expertise and code is a testament to the open-source spirit that drives innovation. Tech enthusiasts can now learn from his experiences and build upon his work. On the other hand, some have expressed concerns about the potential risks of AI-induced psychosis, a condition that can have serious consequences. Tan's comparison of AI work to his past experiences as a startup founder is insightful. He recalls the grueling hours and sleepless nights that came with building a successful company. However, he notes that AI has changed the game, allowing him to be productive without the need for stimulants like modafinil. In Nigeria, where the tech industry is rapidly growing, Tan's enthusiasm for AI is particularly relevant. The country has seen significant investment in AI research and development, with many startups and entrepreneurs exploring its potential. Tan's work with Claude Code serves as a reminder of the opportunities and challenges that come with AI adoption. As the tech ecosystem continues to evolve, it's essential to discuss the implications of AI on our lives and work. Tan's experience highlights the need for balance and responsible innovation, ensuring that the benefits of AI are realized while mitigating its potential risks.