When humans and AI collaborate, the level of abstraction used corresponds and defines the level of autonomy for the agent. The human can give specific step-by-step instructions or describe an idea very vaguely, the agent will adapt and either follow steps closely or get creative.
See also: AI Engagement Patterns
Inspired by Karpathy’s concept of an idea file:
I wanted share a possibly slightly improved version of the tweet in an “idea file”. The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person’s agent customizes & builds it for your specific needs.
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It’s intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.