rvcdbn

Please don't take this as dismissive, but I really think ChatGPT does a better job at explaining this than I can do. Here's what I got:

https://chat.openai.com/share/c1c779c7-3b5f-4ea7-a864-38561d...

The response you posted seems to be referring to various concepts from theoretical physics and philosophy, specifically the ideas of the Everettian interpretation of quantum mechanics, anthropic reasoning, and the Born rule. Let's break these down:

Everettian interpretation of quantum mechanics: Also known as the Many-Worlds interpretation, it suggests that all possible alternate histories and futures are real, each representing an actual "world" or "universe". In layman's terms, it's the idea that there could be countless parallel universes where every possible outcome of an event happens.

Anthropic reasoning: This is a philosophical consideration that observations of the universe must be compatible with the conscious and sapient life that observes it. In other words, our ability to exist and observe influences how we should interpret the universe.

Born rule: In quantum mechanics, the Born rule is a statistical law that connects the mathematical formalism of quantum theory to experimental observations. It provides the probability that a measurement on a quantum system will yield a given result.

The responder seems to suggest that in a universe with many possible futures (as the Everettian interpretation would suggest), we are more likely to observe "black swan" events that lead to more possible futures.

The idea here is that if an event significantly increases the number of possible futures (like a breakthrough that extends human lifespan), then it effectively increases the number of "observer-moments". In other words, more possibilities for observers to exist and make observations. According to anthropic reasoning, this could make these events more likely to occur than pure chance would predict, because we're only able to observe futures in which we exist.

This line of reasoning is highly speculative and philosophical in nature, touching on deep and unresolved questions in physics and philosophy. It's an interesting thought experiment, but it's important to note that this isn't widely accepted or proven in the scientific community as of my knowledge cutoff in September 2021.

I was wrong to say that “nobody starts using because they have a great life and they’re just curious what a bit of meth feels like”. The point I was trying to make was that many people do know exactly what they’re getting into and do it anyway because they also know they have nothing better to look forward to in life and this is really a form of suicide. I was wrong to suggest that this pattern fits everyone, it is indeed an oversimplification and I apologize for minimizing different experiences.

You’re right, I get emotional about this because I see how much harm criminalization does.

There is an anthropic line of reasoning over Everettian branch universes where you can actually expect these types of highly unlikely events to happen more often than chance alone would predict if they promote futures with more Born-rule weighted observer-moments.

Actually one thing I would be curious to try is to substitute ketamine for opiates. It might work out that some people prefer it and it’s far less harmful on the body. Problem is it’s super expensive compared to opiates.

I think these are not the same people we’re talking about here (the people on the streets in SF).

I visited before the pandemic when last did you visit SF because I think it’s a totally different scale.

EDIT: just googled the stats and the number of homeless in SF is roughly the same as the whole of Portugal

All I know is that if I were born into their circumstances I would probably do the same thing. Some lives are way worse than others due purely to accident of birth and the really uncomfortable truth is that we have built a society where some lives are not even worth living. We need to face up to that, not pretend like everyone suffers to anything like the same degree. Life in the USA is very unequal. I’ve suffered terrible events in my life but I also have hope that my future will be worth living. If I didn’t have that hope, I’d be doing exactly what these folks are.

How many people do you know who work in harm reduction? How many of your friends are regular drug users? I’m speaking from direct experience are you? or are you just making assumptions that make you feel more comfortable?

The solution that seems most likely to work IMO seems to be a European-style welfare state. All drugs have long been decriminalized in Portugal and you don’t see that kind of thing on the streets of Lisbon. But I don’t see that happening any time soon in the USA.

We have built a society where the best options for these people are to do what they are doing. Nobody starts using because they have a great life but they’re just curious what a bit of meth feels like and then accidentally get hooked. They do it because there’s no better life path open to them. It’s really a form of suicide. Criminalizing will make the suicide process faster and less visible to you. It won’t stop anyone from using but it will make using more dangerous. There is no easy solution. We need societal change. Making it illegal would be like criminalizing sugar because of the obesity epidemic.

Maybe, maybe not. Companies are not monoliths. For all we know, internally it’s already well known that model weights likely aren’t copyrightable and the only reason for the restrictions is to give the appearance of being responsible to appease the AI doomers.

specifically:

> A century later, in Feist Publications v. Rural Telephone Service Co., the Supreme Court confirmed that originality is a constitutional requirement

Constitutionality is also about how previous cases have been evaluated for example see the bit about how photography copyright was established here: https://constitution.congress.gov/browse/essay/artI-S8-C8-3-...

recent versions of proto3 have added back the “optional” keyword that can be used on any field. see: https://github.com/protocolbuffers/protobuf/blob/main/docs/f...

1 - because they lack originality, see: https://constitution.congress.gov/browse/essay/artI-S8-C8-3-...

I have a hard time imagining a world where it is not the case at least in the US i.e. where copyright is extended to a work with no originality in direct contradiction to copyright clause in the constitution.

At least in the US copyright is established by the constitution so not sure how much it’s possible to change via the normal legislative process.

That’s a bad analogy because a human chose the values of those settings using their creative mind. That’s not at all the case with weights. This originality is the heart of copyright law.

sure but the previous comment made it sound like it was already illegal which would have been really surprising to me. I’m no fan of recent regressions in abortion law but the arguments made by pro-lifers that I’ve heard would not apply to birth control (ie that abortion is essentially killing a human). so I would actually expect them to favor birth control as a way to prevent abortion. that’s assuming their position is really based on their stated beliefs and not something else unstated or irrational (and I decline to take a position on this question at this time).

do you know of any states where it isn’t legal? google searching lead me to this: https://www.nytimes.com/2022/06/24/us/birth-control-plan-b-r... which seems to suggest that it’s legal everywhere

Once decoherence has occurred I don’t think it’s meaningful to say that the system exists in a superposition of states. The multiple decohered branches of the wave function can no longer interfere with each other and so there’s no way for them to affect each other, which is why we call them separate worlds. Within each decohered branch there’s an experimental apparatus and a human that sees one specific outcome. This was Everett’s main insight that each observer in each branch experiences what looks like a collapse but is really just their brain becoming entangled with one or other of the measurements.

if i have a crackpot theory and i’d like a real physicist to look it over and am willing to pay for their time where would i find one? asking for a friend

I’m a “believer” in the Everett Interpretation (on the grounds that it’s the simplest interpretation) but I can’t see how such an experiment could prove anything. This experiment seems to assume we can keep the whole apparatus including the Geiger counter and the mechanism to move the cannon ball from becoming entangled with the environment (decohering). This seems very far outside the realm of current technology.

I think that just further shows your worldview that defaults to information/data as property. I think this is wrong both in the sense that it isn't really what the law says (but aren't going to agree here anyway) but more importantly I think what it should say. Information should not be and is not property by default. There are only three specific ways in which it can become property ("intellectual property"): copyright, trademark and patent. If it's none of those then the government doesn't get to make any rules about how anyone deals in the data because of the 1st Amendment. That's my understanding of the US system at least.

I’m going to go out on a limb here and assume that you’re making this statement because it feels like they should have some intellectual property rights in this case. Independently of whether that feeling corresponds to legal reality (the original question) I would also encourage you to question the source of this feeling. I believe it is rooted in an ideology where information is restricted as property by default. This is a dangerous ideology that constantly threatens to encroach on intellectual freedom e.g. software patents, gene patents. We have a wonderful tradition in the US that information is free by default. It has been much eroded by this ideology but I believe freedom is still legally the default unless the information falls under the criteria of trademark, copyright or patent. I think it’s important to recognize how this ideology of non-freedom has perniciously warped people’s default expectation around information sharing.

sometimes I like to fantasize that over millions of years humanity will spread throughout the cosmos and when there are gazillions of humans (or our machine descendants) with unlimited time and resources there will be in some university somewhere an archeology department that specializes directly in each and every one of us. it’s simply an extrapolation of current trends in academia combined with a possible future where there are a billion people alive for each single one of us alive now. what do you want your personal archeology department to be like? personally i want a graham hancock style character to come up with wacky theories about me so i try to leave as many confusing bits of evidence as possible.

We don’t actually know that it’s not legal. The copyrightability of model weights is an open legal question right now afaik.

You could ask the same kind of question about General Relativity. Sure mass/energy causes the curvature of spacetime but tell me how it does or your theory is worthless. Even without the “how” GR still makes testable predictions that are born out by experiment. And this is the shape of all our physical theories. I think this is the kind of theory IIT is trying to be.

Why wouldn’t you use colab for nsfw? Do you really not trust Google Cloud that much? Or do they have some kind of policy I’m not aware of (can’t imagine how they would enforce this)?