chemical_cutthroat

Can you imagine the alternate headline of “US sends peace keeping force to Saudi Arabia to protect African migrants”? That’s a sociopolitical minefield if there ever was one. I’m sure that if the US knew, so did most everyone else, and there weren’t any other countries lining up to help. SA isn’t known for being a clandestine government, more of a “What are you gonna do about it, buy more oil?” kind of operation. The US is damned if we do, damned if we don’t. Step in and its Team America World Police, don’t do anything and we are standing by letting genocidal governments kill nations.

Don’t forget a map that leads you to all of the DLC you haven’t bought.

Maybe I’m just over-hopeful, but I think “generations” is far too much of an overunderstatement. With the way that technology moves, I don’t think we’ll be waiting that long.

Chrono Trigger, Chrono Cross, FFVI and Xenogears top out the list for me. You can’t beat them. If you want something a little off the beaten path, the soundtrack to Ruiner is pretty fucking rad.

People that say that have never used AI art generation apps and are only regurgitating what they hear from other people who are doing the same. The amount of arm chair AI denialists is astronomical.

I’m getting really close to just not using the internet anymore. I only use it to stream movies, and doom scroll lemmy right now, anyway. The only reason I have an email is for spam. Take awake the only facade of privacy I have and I may as well hang it all up and walk away.

I’m so stoked for this one. I’m keeping my expectations in check, because PC port releases for AAA games have been pretty rough lately, but I hope this plays well out of the gate.

Heroes changed the way I look at writer’s strikes…

Parked

I’m still waiting on proof for any of these allegations. So far it’s just been people suing for the sake of suing and hoping they strike gold. If anyone can point to any evidence at all (read: not hearsay) then I’ll gladly review it, but as it stands, its nothing.

It’s not Earth that’s in trouble…

@Kichae

Those probability distributions are based entirely on what training data has been fed into them.

The exact same thing a human does when writing a sentence. I’m starting to think that the backlash against AI is simply because it’s showing us what simple machines we humans are as far as thinking and creativity goes.

You can see what this really means in action when you call on them to spit out paragraphs on topics they haven’t ingested enough sources for. Their distributions are sparse, and they’ll spit out entire chunks of text that are pulled directly from those sources, without citation.

Do you have an example of this? I’ve used GPT extensively for a while now, and I’ve never had it do that. If it gives me a chunk of data directly from a source, it always lists the source for me. However, I may not be digging deep enough into things it doesn’t understand. If we have a repeatable case of this, I’d love to see it so I can better understand it.

It occurs at the point where the work is copied and used for purposes that fall outside what the work is licensed for. And most people have not licensed their words for billion dollar companies to use them in for-profit products.

This is the meat and potatoes of it. When a work is made public, be it a book, movie, song, physical or digital, it is placed in the public domain and can be freely consumed by the public, and it then becomes part of our own particular data set. However, the public, up until a year ago, wasn’t capable of doing what an AI does on such a large scale and with such ease of use. The problem isn’t that it’s using copyright material to create. Humans do that all the time, we just call it an “homage” or “parody” or “style”. An AI can do it much better, much more accurately, and much more quickly, though. That’s the rub, and I’m fine with updating the laws based on evolving technology, but let’s call a spade a spade. AI isn’t doing anything that humans haven’t been doing for as long as their has been verbal storytelling. The difference is that AI is so much better at it than we are, and we need to decide if we should adjust what we allow our own works to be used for. If we do, though, it must effect the AI in the same way that it does the human, otherwise this debate will never end. If we hamstring the data that an AI can learn from, a human must have the same handicap.

@mack123

Can I get an AI to eventually write another book in Terry Pratchett’s style? Would his estate be entitled to some form of compensation?

No, that’s fair use under parody. Weird Al isn’t compensating other artists for parody, so the creators of OpenAI shouldn’t either, just because their bot can make something that sounds like Pratchett or anyone else. I wrote a short story a while back that my friend said sounded like if Douglas Adams wrote dystopian fiction. Do I owe the Adams’ estate if I were to publish it? The same goes for photography and art. If I take a picture of a pastel wall that happens to have an awkward person standing in front of it, do I owe Wes Anderson compensation? This is how we have to look at it. What’s good for the goose must be good for the gander. I can’t justify punishing AI research and learning for doing the same things that humans already do.

If I do a book report based on a book that I picked up from the library, am I violating copyright? If I write a movie review for a newspaper that tells the plot of the film, am I violating copyright? Now, if the information that they have used is locked behind paywalls and obtained illegally, then sure, fire ze missiles, but if it is readily accessible and not being reprinted wholesale by the AI, then it doesn’t seem that different from any of the other millions of ways we use data in every day life. Just because a machine learned it instead of a human, I don’t believe that it makes it inherently wrong. I am very open to discussion on this, and if anyone has a counter-argument, I’d love to hear it, because this is a new field of technology that we should all talk about and learn to understand better.

Edit: I asked GPT-4 what it thought about this, and here is what it said:

As an AI developed by OpenAI, I don’t access any copyrighted databases, subscription sites, confidential information, or proprietary databases for my learning or response generation. I was trained on a diverse range of internet text, which includes publicly available data in multiple languages and formats. The training also involves learning from large-scale datasets that contain parts of many kinds of texts (books, websites, scientific articles, etc.). However, I don’t know specifics about which documents were in my training set or have access to any specific documents or sources.

Your question seems to pertain to how copyright law applies to AI. This is a complex and evolving area of law and policy, largely because AI systems like me do not “read” or “use” material in the same way a human would. A human might read a book and then consciously recall information from it when writing or speaking. In contrast, AI models do not have consciousness or awareness, they analyze statistical patterns in the data they were trained on and use these patterns to generate responses.

When a human uses copyrighted material to create something new, the law often considers this to be a derivative work. It is typically necessary to obtain permission from the copyright holder to create derivative works. However, AI doesn’t use or recall copyrighted material directly; instead, it learns patterns from a huge amount of text data to predict or generate text based on a given prompt.

Dissemination of copyrighted material, such as through forum posts or Q&A platforms, without proper licensing or within the bounds of fair use, can be a violation of copyright law. AI doesn’t ‘disseminate’ copyrighted material; it generates responses based on patterns it has learned.

That said, the legal interpretation of how copyright law applies to machine learning and AI is still evolving, and there can be a lot of complexities and nuances. Therefore, the information here should not be taken as legal advice.

As of my last update in September 2021, this was the case. However, I recommend checking the most recent legal standpoints and opinions, as this area is still evolving rapidly.

I paid $58 for 2.4ml of canon ink in a 2 pack of black and color ink. That’s still MASSIVELY more expensive than even high end Mont Blanc ink.

You want blood? I got a blood guy.

Two hackers, one keyboard.