I don’t have a good answer for the question (indeed I think agent is a pretty overloaded term, and in many cases underspecified), but I’m not sure I understand why you think there’s a circularity with respect to the definition of an agent that isn’t present for other abstractions. Abstractions do not require an agent as part of their definition (though individual abstractions might).
Well, with something like “hammer”, there’s implicitly an agent (the one recognizing the thing as a hammer), but the agent isn’t part of the hammer. So there’s no loopiness. You can (in principle) define the hammer abstraction and the agent separately, assuming you can somehow define the agent at all.
But when trying to define what an agent is… and then using the abstraction layers that agents use to make sense of reality to define it…
…uh…
…what exactly are you doing, then?
Not to say this makes it impossible. But I’ve yet to see a definition of “agent” that even acknowledges this loopiness, let alone addresses it.
I still don’t see how this is “loopy”, except in the very weak sense that you may be using the things that you mention. Self-reflective yes, but not circular. It’s just another example of noticing that you share some common features with many other entities in the world.
I don’t think abstraction and ability to use definitions is any necessary part of being an agent. Insects are agents. Rocks aren’t. There are some sorts of fuzzy boundary between and around, but those boundaries are nowhere near the uses of the word “agent” as applied to AGI and alignment. It does so happen that some highly complex types of agents can use definitions and have models of the world that are adaptable and highly structured, and the types of agents considered when talking about AGI and alignment are usually assumed to do so, but it doesn’t seem necessary to the concept of agency itself.
I don’t have a good answer for the question (indeed I think agent is a pretty overloaded term, and in many cases underspecified), but I’m not sure I understand why you think there’s a circularity with respect to the definition of an agent that isn’t present for other abstractions. Abstractions do not require an agent as part of their definition (though individual abstractions might).
Well, with something like “hammer”, there’s implicitly an agent (the one recognizing the thing as a hammer), but the agent isn’t part of the hammer. So there’s no loopiness. You can (in principle) define the hammer abstraction and the agent separately, assuming you can somehow define the agent at all.
But when trying to define what an agent is… and then using the abstraction layers that agents use to make sense of reality to define it…
…uh…
…what exactly are you doing, then?
Not to say this makes it impossible. But I’ve yet to see a definition of “agent” that even acknowledges this loopiness, let alone addresses it.
I still don’t see how this is “loopy”, except in the very weak sense that you may be using the things that you mention. Self-reflective yes, but not circular. It’s just another example of noticing that you share some common features with many other entities in the world.
I don’t think abstraction and ability to use definitions is any necessary part of being an agent. Insects are agents. Rocks aren’t. There are some sorts of fuzzy boundary between and around, but those boundaries are nowhere near the uses of the word “agent” as applied to AGI and alignment. It does so happen that some highly complex types of agents can use definitions and have models of the world that are adaptable and highly structured, and the types of agents considered when talking about AGI and alignment are usually assumed to do so, but it doesn’t seem necessary to the concept of agency itself.