Could it be possible to build an AI with no long-term memory? Just make it’s structure static. If you want it to do a thing, you put in some parameters (“build a house that looks like this”), and they are automatically wiped out once the goal is achieved. Since the neural structure in fundamentally static (not sure how to build it, but it should be possible?), the AI cannot rewrite itself to not lose memory, and it probably can’t build a new similar AI either (remember, it’s still an early AGI, not a God-like Superintelligence yet). If it doesn’t remember things, it probably can’t come up with a plan to prevent itself from being reset/turned off, or kill all humans. And then you also reset the whole thing every day just in case.
This approach may not work in the long term (an AI with memory is just too useful not to make), but it might give us more time to come up with other solutions.
This is similar to the concept of myopia. It seems a bit different though, as myopia tends to focus on constraining an AI’s forward-lookingness, whereas your focus is on constraining past memory.
I think myopia has potential, but I’m not sure about blocking long-term memory. Does forgetting the past really prevent an AI from having dangerous plans and objectives? (I haven’t thought about this very much yet, it’s just an initial reaction.)
Could it be possible to build an AI with no long-term memory? Just make it’s structure static. If you want it to do a thing, you put in some parameters (“build a house that looks like this”), and they are automatically wiped out once the goal is achieved. Since the neural structure in fundamentally static (not sure how to build it, but it should be possible?), the AI cannot rewrite itself to not lose memory, and it probably can’t build a new similar AI either (remember, it’s still an early AGI, not a God-like Superintelligence yet). If it doesn’t remember things, it probably can’t come up with a plan to prevent itself from being reset/turned off, or kill all humans. And then you also reset the whole thing every day just in case.
This approach may not work in the long term (an AI with memory is just too useful not to make), but it might give us more time to come up with other solutions.
This is similar to the concept of myopia. It seems a bit different though, as myopia tends to focus on constraining an AI’s forward-lookingness, whereas your focus is on constraining past memory.
I think myopia has potential, but I’m not sure about blocking long-term memory. Does forgetting the past really prevent an AI from having dangerous plans and objectives? (I haven’t thought about this very much yet, it’s just an initial reaction.)