After playing a bit with AI agents like Claude Code, Codex, Gemini-cli, warp terminal (warp. dev), and MCP, I feel that:
- LLMs are the brain (but alone, they cannot interact with the outside world)
- MCP servers are the tools (that help the brain interact with the world)
- Agents are the hands (that link the brain with the tools)
P.S.
Don't get me wrong, I don't think we're there, just yet, that AI is even remotely close to replacing us (although in some aspects it is), or agree with this hype on AI, where people are giving it way too much credit.
However, it's wise to use it for what it's good at, but not to have absurd expectations when it's not yet good enough.
Because it's here to stay, just like the Internet, and it can significantly enhance us.
And we should not forget:
"It is not the strongest of the species that survives,
not the most intelligent that survives.
It is the one that is the most adaptable to change."
Humans are best at (compared to other animals):
- making tools
- collaboration The internet and its services are the best collaboration medium, and AI models are the most effective tools.
Top comments (0)