I came up with this after watching a science fiction film, which shall remain nameless due to spoilers, where the protagonist is briefly in a similar situation to the scenario at the end. I'm not sure how original it is, but I certainly don't recall seeing anything like it before....
Tech News Daily have published an article advocating AI-boxing, which namechecks Eliezer's AI-Box Experiment. It seems to claim AI-Boxes are a revolutionary new idea; is covered in pictures of fictional, evil AIs; and worries that a superintelligent AI might develop psychic powers. Seems like a good reminder of the state...
It's pretty standard to respond to the suicides of Y victims by rallying to reduce Y.
Making a commitment not to notice when something drives a person to suicide seems like it would probably be a monumental mistake.
I don't think so - I think Eliezer's just being sloppy here. "God did a miracle" is supposed to be an example of something that sounds simple in plain English but is actually complex:
One observes that the length of an English sentence is not a good way to measure "complexity". [...] An enormous bolt of electricity comes out of the sky and hits something, and the Norse tribesfolk say, "Maybe a really powerful agent was angry and threw a lightning bolt." The human brain is the most complex artifact in the known universe. [...] The complexity of anger, and indeed the complexity of intelligence, was glossed over by the humans who hypothesized Thor the thunder-agent.
To a human, Maxwell's Equations take much longer to explain than Thor.
Will this "Arbital 2.0" be an entirely unrelated microblogging platform, or are you simply re-branding Arbital 1.0 to focus on the microblogging features?
Off the top of my head: Fermat's Last Theorem, whether slavery is licit in the United States of America, and the origin of species.
It's almost like having a third sex. In fact the winged males look far more like females than they look like wingless males.
That sounds like exactly the kind of situation Eliezer claims as the exception - the adaptation is present in the entire population, but only expressed in a subset based on the environmental conditions during development, because there's a specific advantage to polymorphism.
There's the whole phenomenon of frequent-dependent selection. Most people are familiar with this from blood types, and sickle-cell anaemia.
Those are single genes, not complex adaptations consisting of multiple mutually-dependant genes. Exactly the "froth" he describes.
Psy-Kosh: Hrm. I'd think "avoid destroying the world" itself to be an ethical injunction too.
The problem is that this is phrased as an injunction over positive consequences. Deontology does better when it's closer to the action level and negative rather than positive.
Imagine trying to give this injunction to an AI. Then it would have to do anything that it thought would prevent the destruction of the world, without other considerations. Doesn't sound like a good idea.
No more so, I think, than "don't murder", "don't steal", "don't lie", "don't let children drown" etc.
Of course, having this ethical injunction - one which compels you to positive action to defend the world - would, if publicly known, rather interfere with the Confessor's job.
Well, that and the differences in the setting/magic (there's no Free Transfiguration in canon, for instance, and the Mirror is different - there are less Mysterious Ancient Artefacts generally - and Horcruxes run on different mechanics ... stuff like that.)
And Voldemort is just inherently smarter than everyone else, too, for no in-story reason I can discern; he just is, it's part of the conceit. (Although maybe that was Albus' fault too, somehow?)
To be fair, we don't know when he wrote the note.
I don't like the idea of it happening. But if it does, I can certainly disclaim responsibility since it is by definition impossible that I can affect that situation if it exists.
Actually, with our expanding universe you can get starships far enough away that the light from them will never reach you.
But I see we agree on this.
That appears to me to be an insoluble problem. Once intelligence (not a particular person but the quality itself) can be impersonated in quantity, how can any person or group know he/they are behaving fairly? They can't. This is another reason I'd prefer that the capability continue not to exist.
But is it possible to impersonate... (read more)
I came up with this after watching a science fiction film, which shall remain nameless due to spoilers, where the protagonist is briefly in a similar situation to the scenario at the end. I'm not sure how original it is, but I certainly don't recall seeing anything like it before.
Imagine, for simplicity, a purely selfish agent. Call it Alice. Alice is an expected utility maximizer, and she gains utility from eating cakes. Omega appears and offers her a deal - they will flip a fair coin, and give Alice three cakes if it comes up heads. If it comes up tails, they will take one cake away her stockpile. Alice runs the numbers, determines that... (read 445 more words →)
Tech News Daily have published an article advocating AI-boxing, which namechecks Eliezer's AI-Box Experiment. It seems to claim AI-Boxes are a revolutionary new idea; is covered in pictures of fictional, evil AIs; and worries that a superintelligent AI might develop psychic powers.
Seems like a good reminder of the state of reporting on such matters.
Any suicide in general, and this one in particular, definitely has multiple causes. I'm really sorry if I gave the opposite impression.
But I think it's reasonable and potentially important to respond to a suicide by looking into those causes and trying to reduce them.
To be more object-level:
- Kathy was obviously mentally ill, and her particular brand of mental illness seems to have been well-known. I don't know what efforts were made to help her with that (I do get the impression some were made), but I've seen people claim her case was an example of the ways our community habitually fails to help people with mental illness and it certainly seems worth
... (read more)