Designing the script for each individual task and subtask in order to make a 90% reliable AI economically valuable turns a productivity-improving tool into an economically productive agent, but only within certain parameters, and each time you encounter a new task, more scafolding will need to be built.
Agreed that that wouldn’t be good evidence that those systems could do general reasoning. My intention in this piece is to mainly consider general-purpose scaffolding rather than task-specific.
Very interesting example, thanks.
Agreed that that wouldn’t be good evidence that those systems could do general reasoning. My intention in this piece is to mainly consider general-purpose scaffolding rather than task-specific.