Horseless Carriages

the Gmail team has shipped a product that perfectly captures the experience of managing an underperforming employee.

The modern software industry is built on the assumption that we need developers to act as middlemen between us and computers. They translate our desires into code and abstract it away from us behind simple, one-size-fits-all interfaces we can understand.

In the new world I don’t need a middleman tell a computer what to do anymore. I just need to be able to write my own System Prompt, and writing System Prompts is easy!

My core contention in this essay is this: when an LLM agent is acting on my behalf I should be allowed to teach it how to do that by editing the System Prompt.

Tools provide the security layer for agents. Whether or not an agent can do a particular thing is determined by which tools it has access to. It is much easier to enforce boundaries with tools written in code than it is to enforce them between System and User Prompts written in text.

This is what AI’s “killer app” will look like for many of us: teaching a computer how to do things that we don’t like doing so that we can spend our time on things we do.