MCPs: Who Controls the Future of AI?

2025-04-23
MCPs: Who Controls the Future of AI?

This article delves into the potential and limitations of Model Context Protocols (MCPs). MCPs, standardized APIs connecting external data sources to LLMs like ChatGPT, empower LLMs to access real-time data and perform actions. The author built two experimental MCP servers: one for code learning, the other connecting to a prediction market. While promising, MCPs currently suffer from poor user experience and significant security risks. Critically, LLM clients (like ChatGPT) will become the new gatekeepers, controlling MCP installation, usage, and visibility. This will reshape the AI ecosystem, mirroring Google's dominance in search and app stores. The future will see LLM clients deciding which MCPs are prioritized, even permitted, leading to new business models like MCP wrappers, affiliate shopping engines, and MCP-first content apps.

Read more

AI Coding's Bottleneck: Clear Communication Trumps Perfect Prompts

2025-04-11
AI Coding's Bottleneck: Clear Communication Trumps Perfect Prompts

The author details significant progress in AI development, rapidly building multiple products using AI tools. However, they found that AI tools often act like junior developers lacking product context and user insight, prone to errors on non-standard tasks. This recalls a university class using a peanut butter and jelly sandwich analogy to illustrate the importance of clear coding instructions. While today's AI is more advanced, it still requires developers to provide clear, precise instructions to avoid a messy outcome. The author argues that success in the AI era will depend on developers' ability to clearly understand and explain how to transform fuzzy ideas into workable products, not just coding speed.

Read more
Development prompt engineering