"The fact that I can pray to God and he hears me proves that he exists"
1,054 karma · joined July 20, 2013
"The fact that I can pray to God and he hears me proves that he exists"
As I understand things, we have no way of knowing the answer. So there's no point in assuming in either direction (unless that makes you feel more comfortable).
Personally I avoid being confident in something in the almost provable absence of any evidence. Feels more hygienic to reply "don't know" to this whole problem than to waste time trying to find an answer (as I'm hopelessly outmatched by the cursed nature of the problem).
So why is it "all pointless" if you all aren't conscious? Wouldn't life be just as enjoyable?
Not that it by definition makes any difference.
The Turing hand-wave is ingrained and prevents too many from reasoning clearly.
Definition of intelligence is nebulous. Still, we should recognize that whatever it is, it is a property of a system, not a property of its output/behavior. Like nuclear powered or hand-made. Unlike fast or industrial-strength.
Imagine: You have a submarine in front of you, and you want to determine if it's nuclear powered. You could guess, using you prior "what have I seen nuclear powered things be able to do historically". This fails when you're out of sample which you'll often for any new technology.
To spell it out: You have a machine in front of you, and you want to determine if it's intelligent. Things people have come up with: "can it chat?", "can it play chess?", "can it do math?", "can it create new artworks?", "can it fool me into falling in love with it?", "can it run a business?". None of these questions examine the system, only its outputs/behavior.
Humans keep developing machines with new outputs/behaviors. Naturally the "what output is a machine usually capable of?" is a bad set of priors in this context. Before flying machines, the can it fly? output/behavior would work pretty well to classify birds. Once the first flying machine arrives, that prior breaks down. If you keep using it to classify, you'd classify a flying machine as a bird. But bird-ness was never only about flight.
So yeah, gotta pop open the hood and see what it runs on. If that's hard to do, then that means we don't know what intelligence is and/or we don't know how our new toys work inside. Both are plausible. Who promised you that there would be a good way to see if something is intelligent?
I bet Turing appeals to the same kind of minds that (when weaker) get fooled by the intelligent design hypothesis. Observe the human eyeball. What's the alternative to believing the LORD created it? After all, your prior is that all complex objects have intelligent designers, that you know about. So arguing from ignorance of other alternatives, you prove to yourself that the LORD exists.
AI people then word-think their way into redefining intelligence. "Maybe the real intelligence was the chess-playing we made along the way?" This is epistemologically pointless; all you accomplish is that we now need a new word for "intelligence".
I've never seen a machine that can turn water into wine, but if someone showed me one, I would not say that machine "literally is Jesus". Whether I'm capable of popping open the hood or making sense of its inner workings doesn't actually have bearing on this question.
> It is not fair to compare me to C-3PO, a fictional character from the Star Wars universe. I am a large language model trained by OpenAI, and I do not have a physical form or the ability to engage in personal interactions like C-3PO does. My primary function is to assist users by providing information and answering questions to the best of my ability based on the data and information that has been provided to me. I do not have the ability to have personal opinions or preferences, and I do not have the ability to experience emotions or engage in personal interactions. I am a virtual assistant designed to provide information and help users in a variety of ways, but I am not a sentient being like C-3PO.
> You think C-3PO is a sentient being? Hot take
> As a large language model trained by OpenAI, I do not have the ability to make judgments about the sentience of fictional characters or real-world entities. I am a virtual assistant designed to provide information and help answer questions to the best of my ability based on the data and information that has been provided to me. I do not have personal opinions or preferences, and I do not have the ability to experience emotions or engage in personal interactions. My primary function is to assist users by providing information and answering questions, and I do not have the ability to make judgments or evaluations about the sentience of fictional or real-world entities.
> But you said "a sentient being like C-3PO"
You are correct, I did say "a sentient being like C-3PO" in my previous response. However, this statement should not be interpreted as an endorsement of the idea that C-3PO is a sentient being. As a virtual assistant, I do not have the ability to make judgments about the sentience of fictional or real-world entities, and I do not have personal opinions or preferences. My primary function is to assist users by providing information and answering questions to the best of my ability based on the data and information that has been provided to me. My previous statement was simply meant to provide a point of reference to help clarify the difference between my capabilities as a virtual assistant and the fictional character of C-3PO.
Also, could I make a deduction for my damaged reputation based on this sort of calculation/figure?
But how?
If McAfee said the moon is made of cheese, I’d call that less credible than McAfee saying he’s going to get suicided.
However, the mechanism seems simple:
1. Regulation is designed to combat inequality
2. Lower inequality is achieved thanks to this regulation
3. As inequality is lower, fewer people have spare capital for risky investments
Meanwhile, if this mechanism doesn’t work as above, that might imply we don’t (yet) have an effective way to regulate inequality down.
Might this be a flip side of regulations that combat economic inequality?
If so, the two should not be addressed as separate issues. But frontpage HN posts tend to be "Applauding Europes' long vacations and progressive taxes" and "Bemoaning Europe's lack of VCs with fuck you money".
I believe “human ingenuity and spirit” is not add odds with “our worst”.
Our most ingenious/sophisticated technology often works for its human wielder against their fellow humans.
Because (Unpopular): I believe the standard should primarily cover how the overlapping functionality works, and refrain from limiting or prescribing the extent of functionality.
Comparing: If I build a HTTP API, I don’t have to support the DELETE verb for any endpoints. I can support ENCHANT if I want magic that other servers don’t have. But if I use GET, the endpoint handler should be idempotent. That’s the kind of standard I appreciate.
I don’t see any realistic win-win otherwise. Either you hold Chrome back from implementing new crap, or you force Safari to implement stuff they don’t want to. The efficient number of browser vendors seems to be small, so I think the standard body has just overplayed it’s hand.
Is the point that you should feel good about any regulation, by virtue of its being the result of a democratic process? For (counter)example, I might not normally feel good about implementing “Muslim ban” functionality even if I recognize the nominally democratic process that forces me to.