I was trying to contrast the myopic paperclip maximizer idea with the classic paperclip maximizer. Perhaps “long-term” was a lousy choice of words. What would be better: simple paperclip maximizer, unconditional paperclip maximizer, or something?
Update: On second thought, maybe what you were getting at is that it’s not clear how to deliberately train a paperclip maximizer in the current paradigm. If you tried, you’d likely end up with a mesa-optimizer on some unpredictable proxy objective, like a deceptively aligned steel maximizer.
I was trying to contrast the myopic paperclip maximizer idea with the classic paperclip maximizer. Perhaps “long-term” was a lousy choice of words. What would be better: simple paperclip maximizer, unconditional paperclip maximizer, or something?
Update: On second thought, maybe what you were getting at is that it’s not clear how to deliberately train a paperclip maximizer in the current paradigm. If you tried, you’d likely end up with a mesa-optimizer on some unpredictable proxy objective, like a deceptively aligned steel maximizer.