In the Death Note anime, the Death Note gives the protagonist the ability to create a totalitarian justice system. That is, if there isn't a force to stop him. But a character named L quickly catches onto him, and makes his ability to "serve justice" harder. In other words, the...
An advanced alien species clones me on the atomic level, lines me up exactly across myself, in a perfect mirrored room: Diagram of the room, as seen from above. I stare at myself for a second. Then, as a soft "hi" escapes my mouth, I notice that my clone does...
I would just like to point out the trolley problem here.
Yes, pulling the lever will save four people, but the one person who dies would still be alive if it wasn't for us pulling the lever. There's a (somewhat radical) active intervention that makes us responsible for potential bad outcomes.
There seems to be a similar effect with "more dakka". Implementing a modest solution is socially justifiable. Implementing a radical solution may be less so.
It's a dilemma, and even if you're 100% doing the right thing, it may still lead to bad outcomes.
You’ll see… 👽
Jokes aside, I get the point: we have thoroughly outpaced evolution and thus nature, and AGI will do the same.
This article doesn’t present an absolute rule of nature, just a natural inclination. There are plenty of exceptions to the rule, but I think Entropy Theory is relevant to reason about future scenario’s, and I haven’t heard it mentioned much in relation to AGI. So I just wanted to make this argument so we can use it in our future predictions.
In the Death Note anime, the Death Note gives the protagonist the ability to create a totalitarian justice system. That is, if there isn't a force to stop him. But a character named L quickly catches onto him, and makes his ability to "serve justice" harder. In other words, the Death Note is a powerful tool (like AGI), but opposing forces hamper its ability to affect the world.
In the Death Note series, L only responded when he noticed the anomalous effects of the Death Note. He took a reactive approach.
When talking about AGI, usually the discussion gravitates towards "and then the uptick in intelligence goes out of control, leading to completely unpredictable... (read 295 more words →)
I don't think (1) works like that. Because both our reaction algorithms would yield the same actions?
Regarding (2): I suppose for this to work, the clone should be mirrored as well? I guess the advanced aliens can do that.
An advanced alien species clones me on the atomic level, lines me up exactly across myself, in a perfect mirrored room:
I stare at myself for a second. Then, as a soft "hi" escapes my mouth, I notice that my clone does exactly the same. Every motion, everything, is mirrored.
In this experiment, we assume a perfectly deterministic psychological state: eg, given the same conditions, a person will always do exactly the same. (scientifically, that makes most sense to me)
Together with my clone, I'm trying to devise how to escape this unfortunate situation: eg, how to untangle us mirroring each other's motions.
The first idea we devise is... (read 215 more words →)
Great article! The laws you describe are definitely subject to many social behaviors.
One thing I found insufficiently covered in the article is how social prejudices shape the extent to which people act in “dark matter” behavioral patterns. The way it’s described in the article, it seems like either Person A has property X, or they do not have property X, independent of the existing social prejudices. I would like to challenge that assumption.
If I lived many years ago, I might’ve had slaves, and could be put in a bucket “people who enjoy having slaves”. But since social norms changed, nowadays there will for certain be fewer people who “enjoy having slaves” just... (read more)
Logically, maybe not that much.
Socially, this is a believe people hold.
I think it's the main argument for people choosing not to pull the lever (almost 20% by a survey I found).