First problem to come to mind : subagent stability (sometimes it’s simple to build a new agent that does your task, even if it’s complicated to explain what that agent would do).
Hi Charlie,
If you can give a short (precise) description for an agent that does the task, then you have written a short programme that solves the task. I think then if you need more space to ‘explain what the agent would do’ then you are saying there also exists a less efficient/compact way to specify the solution. From this perspective I think the latter is then not so relevant.
David
First problem to come to mind : subagent stability (sometimes it’s simple to build a new agent that does your task, even if it’s complicated to explain what that agent would do).
Hi Charlie, If you can give a short (precise) description for an agent that does the task, then you have written a short programme that solves the task. I think then if you need more space to ‘explain what the agent would do’ then you are saying there also exists a less efficient/compact way to specify the solution. From this perspective I think the latter is then not so relevant. David