Bing Chat posted:

Here are some good roofers in Bethesda, Maryland that I found:

- PG Builders Inc: 7805 Old Georgetown Rd Ste 203, Bethesda, MD 20814. Phone number: (301) 346-1902. Website: https://www.pgbuilders.com/. Rating: 4/5 ¹

- Roofers of Arlington: 1201 S Courthouse Rd, Arlington, VA 22204. Phone number: (703) 475-2446. Website: https://www.roofersofarlington.com/bethesda-md.php. Rating: 5/5 ³

- Bethesda Roofing Services: 4710 Bethesda Ave, Bethesda, MD 20814. Phone number: (301) 200-1140. Website: https://bethesdaroofingservices.com/. Rating: 5/5 ⁴

I hope that helps. Let me know if you have any other questions.

Source: Conversation with Bing, 3/22/2023(1) . https://bing.com/search?q=good+roofers+bethesda+maryland Accessed 3/22/2023.
(2) Roofing Bethesda MD | Roof Bethesda, best roofers near you. https://www.roofersofarlington.com/bethesda-md.php Accessed 3/22/2023.
(3) 10 Best Roofers in Bethesda, MD 2023 - Porch. https://porch.com/bethesda-md/roofers/cp Accessed 3/22/2023.
(4) 453 Best Roofers Near Me in Bethesda , MD - GAF Roofing. https://www.gaf.com/en-us/roofing-contractors/MD/Bethesda Accessed 3/22/2023.
(5) Top 25 Roofers - Bethesda MD with Reviews - HomeAdvisor. https://www.homeadvisor.com/c.Roofing.Bethesda.MD.-12061.html Accessed 3/22/2023.
(6) Best 15 Roofers & Gutter Installation Companies in Bethesda, MD - Houzz. https://www.houzz.com/professionals/roofing-and-gutter/bethesda-md-us-probr0-bo~t_11819~r_4348599 Accessed 3/22/2023.

cinci zoo sniper posted:

Learning doesn't normally use evolutionary algorithms, no. 3.4 of https://dl.acm.org/doi/fullHtml/10.1145/3467477 is a decent starting point.

The topic of the recent posts ultimately seems to be ChatGPT, to the end of which here's, like, blow-by-blow walkthrough of it, oriented at non-specialists. https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/

Chat GPT posted:

Once upon a time, there was a web comedy forum where people gathered to share jokes, memes, and silly videos. The forum had been thriving for years, but as time went on, the members grew older and their interests started to shift. Some moved on to more serious pursuits, while others became disenchanted with the constant stream of juvenile humor.

Despite the changes, there were a group of die-hard members who refused to grow up. They clung to the forum as if it were their last bastion of childishness, unwilling to let go of their youth.

As the years went by, the forum began to wither and die. The once-bustling threads were now filled with empty echoes, and the laughter that once echoed through the digital halls had faded away.

One day, a wise old monk came across the dying forum. He saw the desperate clinging of the members to their past and knew that something had to be done.

He approached the members and asked them, "Why do you cling to this dying forum? Is it not time to move on and explore new avenues of joy and laughter?"

The members protested, saying that they were happy in their own way and that they didn't need to grow up. But the monk was not deterred.

He told them a parable: "Imagine a tree that refuses to let go of its leaves. It clings to them long after they have withered and died, refusing to accept that it is time for a new season. The tree becomes stagnant and is unable to grow or flourish. The same is true for us. If we cling to the past, we will be unable to grow and thrive."

The members were moved by the monk's words and realized that they had been holding themselves back. They knew that it was time to move on and explore new avenues of joy and laughter.

And so, the forum closed its doors, but the members moved on to new adventures, laughing and exploring the world around them. The old ways were gone, but they had found a new path, one that led to growth and new experiences.

SCheeseman posted:

I don't think many want to chat about it, tensions are way too high and it's fracturing communities. Anyone who has their jobs and livelihoods threatened by it and/or see it as an affront to humanity are mostly interested in ways to crush it. Pretty understandable, the capitalist powers that be will take this technology and use it in all the ways people fear it will be.

But figuratively trashing the looms has never worked. AI is the end point of humankind's reliance on tool use, the problems we're grappling with now started when cavemen sharpened their flint to the point they could carve rock and/or skulls. The best we can do is manage it, something we've had a shaky history of doing particularly as of late thanks to a society that predominantly values accumulation of capital over human wellbeing (while those in ivory towers try in vain to equate the two). An AI ban might be technically possible and enforceable, but not when every world government want's this AI thing to happen, and given a social and political system with truly humanistic values automation wouldn't be a problem anyway.

It's the rich people. They are the baddies.

i say swears online posted:

I'm shocked at how well it writes jingles, which has all sorts of knock-on effects. the premise of two and a half men is in shambles

SCheeseman posted:

I disagree that it has to be an external force that stops us when we are entirely capable of nuking ourselves to death, the alternative is to organize our society so whatever us dumbasses make isn't given the opportunity to help destroy us.

As for bans, depends on the implementation. Preventing use by corporations is definitely possible, but that does nothing to stop criminal orgs or individuals, particularly now that the software runs on consumer hardware. It also has the potential to slow down industry growth relative to countries that might choose to accelerate AI R&D instead, hello national security concerns. I agree that I don't see it happening, not with the billionaire class at war with each other in a sort of geopolitical mexican standoff.

idk, if AI eventually heralds true post scarcity by inventing star trek poo poo, cool beans, but at the moment it does essays and spits out pretty pictures. Not to say I don't think people will find ways to use the technology in broader ways that have greater impact, but at the moment, post scarcity is still sci-fi.

SaTaMaS posted:

Is this thread supposed to be about what's happening currently or speculations about things that probably won't ever happen

SCheeseman posted:

I would personally prefer that nuclear weapons were not improved.

Post scarcity is typically associated with the scarcities that are required for human survival like food and shelter, not cultural artifacts or luxuries, and those who are being made redundant are rightfully unhappy that what allowed them to live their lives became "post scarcity" before actual post scarcity was a thing.

I get that AI is useful, I've spent quite a bit of time thinking and talking to other about cool applications of the tech and defending use of it as a means of expression. I also agree it's inevitable, horse has bolted and at this point society must adjust to the technology. Which is why all the anger laid on the tech and particularly those who want to use it is a red herring, shouldn't the aim be higher up the totem pole? Choosing to make staff redundant is a choice made by a human with a gun pointed to the head by shareholders.

If I'm hoping for any outcome, it's one where AI brings about a wave of socialism. Not that I think it's likely.

Kavros posted:

I expect very little good from AI because of what it is being purpose-built towards. it's not going to be here to make our lives easier, it will be here to better extract profit for the benefit of a specific class of investor or owner-of-many-things.

One thing I expect it will be really good at in the meantime is further destroying "community," since so much of community is online and it will be even more numbingly difficult to navigate seas of inauthentic communication and signal-to-noise ratios blown into bits even more efficiently than it was in an age of mere botting

Ohthehugemanatee posted:

On one level, yep it's going to be a societal disaster. I think the implications are worse than folk even imagine. Right now, I can spot a bot. I don't believe I or anyone else will be able to within a year. Scams are going to be wild, journalism is hosed and online forums are going to be ruined. The companionship an AI is eventually going to be capable of offering people is going to take society in weird directions. I'm a huge loving nerd and excited than an AI can run a table top wargame against me but at the same time it would be pretty sad if I turned to that instead of playing games with other people.

But I have seen one cool thing. Bing's chatbot doesn't have some of the hard limits on it that other systems do, and it doesn't balk at doing medical stuff. It's good. It's really good. I've been running patients at it to see if it can make accurate diagnoses and it's great at recognizing rare patterns that humans tend to miss. I had a patient last week who was seen by 3 providers who missed multiple myeloma, and when fed in the lab abnormalities and chief complaint, the program caught it right away. Even with confounding factors or missing elements from the history or labs, Bing was able to catch what one family MD, one family NP and one ED attending all missed. The first doc saw weird labs and thought they were an error because he didn't take a good history that would have raised all the red flags in the world, the NP saw weird labs on repeat and didn't see the pattern, panicked and sent the patient to the ED, and the ED physician saw weird labs, ignored everything but the low red blood cell count and incorrectly diagnosed a gastrointestinal bleed because she was busy and that's something she sees probably twice a night. The AI has none of those limitations. Depending on what elements I give it, it isn't always able to say "Oh poo poo that's multiple myeloma" but it's always able to say "Hm that could be a lot of things but it would be important to rule out multiple myeloma." That's cool as hell.

Raenir Salazar posted:

quote:

A bar examination coordinated by NCBE that is uniformly administered, graded, and scored by user jurisdictions and results in a portable score. It is composed of the MEE, two MPT tasks, and the MBE. See our interactive map for jurisdictions that have adopted the UBE. For more information, view our informational pdf about the UBE.

litany of gulps posted:

Is the primary difficulty of the exam a time-crunch issue? If so, then an AI chatbot has fairly tremendous advantages due to the nature of the exam. I don't think it should be particularly surprising that a chatbot with access to huge amounts of examples and study materials should be able to crank out a bunch of rough draft essay responses to questions that humans struggle with because they have to read prompts and compose written arguments or analysis on the fly.

But what's the takeaway from that specific example? One paralegal now does the job formerly done by two and the partner pockets a bit more profit?

Gumball Gumption posted:

I think it's important to note that it's training included example MEE essays. It's interesting but GPT-4 being trained for the exams and passing them is then not indicative of performance in a court room. It does show that it would be of value as an information store for lawyers.

Really I think that's where the true value in AI is. Not for its ability to create things but for its ability to be a way to store knowledge and interfaces that feel more natural.

Fuzz posted:

I was speaking mainly from the medical perspective, as I've taken and passed all those medical exams too.

They don't actually replace the clinical training at all, and all medical students and residents take those exams but you throw them in a solid 85+% of cases and unless it's super bread and butter stuff they won't actually diagnose the problem correctly, unless you as a patient enjoy the House style trial and error method of medical treatment instead of actually examining thoroughly and running focused tests and then treating the actual issue based on your results instead of jumping to a conclusion based on incomplete data because illiciting all that info from a patient and asking the right questions is like 75% of what experience teaches you.

Could it get there eventually? Who knows, anything is possible, but not in the next few years and there's a big gap between knowing the book and actually being able to take care of people. The same can be said of Nurse Practicioners, since they similarly lack a large amount of clinical experience and training before they're handed a prescription pad and told to just start seeing patients and figure it out as they go..

Raenir Salazar posted:

Liquid Communism posted:

Anyone who understands the technology behind it on more than a surface level is generally right with those authors and artists because they understand that none of this AI functions without massive datasets that invariably violate the rights of authors and artists because no organization could afford to license works on that scale. Even at massively discounted rates for commercial licensing the image DBs behind them would be billions of dollars.

It is hilarious how clearly this is designed to benefit the rentier class, though. Using billions of dollars of supercompute hardware, at a cost of millions a month in power, cooling, and network capacity to avoid paying a few graphic designers $40k a year.

GPT4 being able to pass the Bar is more a function of how the test is written than the ability of the AI. It's specifically designed to test the memory of applicants in a stressful and long-form test. A search algorithm with effectively perfect recall will do well at this.

Doing a lawyer's actual job, making analysis of law and presenting facts in light of said analysis, in a convincing and logical manner aligned to precedent is far outside of its scope. The same for doctors, being able to cross-reference WebMD really fast is no replacement for the people skills required to actually get an accurate description of symptoms from a patient, or to create a treatment plan across multiple conditions present that provides a balance between quality of life, patient comfort, and effectiveness of treatment.

Hell, GitHub's implementation to write code is going to go hilariously badly because it is trivial to poison the data sources in such a way as to make the outputs useless or try to inject exploits into them such that the script recreates them.

Carp posted:

Main Paineframe posted:

If anything, I think the term "AI" is actively detrimental to the conversation. It causes people to lump all this stuff together as if there's no difference between them, and draws their attention away from the actual specific capabilities and technical details.

Carp posted:

I work for a company that processes advertising co-op claims as a software engineer and developer. AI has been a back-burner interest of mine for decades, but I'm far from an expert and have had little experience coding, or coding for, AI systems.

[edit]

Err, meant to add, I'm looking into using GPT as a co-auditor to help human auditors triage claims. None of our customers would be remotely interested in claim processing being completely automated using AI. They hire us for our attention to detail and support a human can provide.

Main Paineframe posted:

Yeah, I'm talking about the specific conversation, not the thread title. We just went from someone talking about ChatGPT doing chemistry to someone linking papers about ML drug discovery models as proof that it's plausible. That's a real apples-and-oranges comparison.

And what I'm getting at is that there's no real evidence that ChatGPT is capable of "doing chemistry" (a phrase that, by itself, really deserves to be specifically defined in this context), outside of a senator having an moment.

Personally, I'm very wary of any claims about "emergent" abilities from ChatGPT, because the one thing natural language processors have proven to be extremely good at doing is tricking us into thinking they know what they're talking about. Extraordinary claims always need evidence, but that evidence ought to be examined especially closely when it comes to extraordinary claims about ChatGPT.

Liquid Communism posted:

Remember that the Bar is not an indication of a good lawyer. It is a minimum standard to be allowed to practice law, and in the case of the 'pass' it is again starting from the massive advantage over a human of being able to look up sources with total recall. I'd imagine the worst law student on the planet could pass the exam if it were open book.

Liquid Communism posted:

Given part of the point of the test is 'does this person remember the principals well enough to make decisions based on them under stress', the recall ability is indeed something being tested. There's a reason that candidates cram for weeks before taking the test to try and have as much possible information in memory as they can.

Liquid Communism posted:

A GPT-4 implementation is incapable of experiencing stress, and again has open access to the materials being tested on, so by its very nature a test of its stress management and memory cannot have any meaningful results.

Liquid Communism posted:

It does have meaningful results for a human, although I'm sure there are better approaches, but that may be my own bias against the validity of standardized tests.

If passing the test were the purpose of the test you would have a point regarding the GPT-4 results.

It is not. The purpose of the bar exam is for a candidate to demonstrate they have the skills necessary to practice law at the standard set by the bar association, as a condition of admission to the bar and licensure to practice law. The ability to manage that stress is part of the point of the test. That GPT-4 cannot experience that stress is not an indicator of superiority, so much as a demonstration that it lacks the basic capabilities that are being tested in the first place. So far as I can tell from the article, it was also only tested on the first two portions of the bar exam, the multiple choice and essay portions, and not the significantly more important performance test where an aspiring lawyer is given a standard task such as generating a brief or memo for a case file set in a fictional state, along with a library of the laws of said fictional state.

I do not expect that by its design the GPT-4 is capable of a relatively simple task of reasoning using a dataset on which it has not been trained.

All somewhat beside the point as the GPT-4 cannot in point of fact practice law, because by definition a lawyer requires personhood, which a chat algorithm is incapable of.

From the Paper Abstract posted:

In this paper, we experimentally evaluate the zero-shot performance of a preliminary version of GPT-4 against prior generations of GPT on the entire Uniform Bar Examination (UBE), including not only the multiple-choice Multistate Bar Examination (MBE), but also the open-ended Multistate Essay Exam (MEE) and Multistate Performance Test (MPT) components.

reignonyourparade posted:

chatpgt-ed again

Aramis posted:

Of course. Both me, and most of my colleagues do at this point.

If your job involves producing textual content, be it articles, code, recipes, whatever, then ChatGPT can almost certainly be used, today, to make your job easier. It might take a bit of time to establish an efficient workflow, but there's no denying that this is a useful tool as it stands.

I've personally moved on from using the web ui to a simple python script that formats frequent queries into templates that I know provide good results and interfaces with the API, but a text file and some copy-pasting can go a long way already.

Frankly, unless you have specific constraints preventing you to do so, you would be a fool to not at least give it a shot. All this to say, I'm scratching my head as to why you found this surprising at all.

edit: Big emphasis on it being a tool. It's not something that replaces work entirely yet, but it is something that you can wield very effectively in a myriad of contexts.

Quixzlizx posted:

I got an invitation to Google Bard, and I'm honestly having trouble thinking up useful things to ask it.

It doesn't help that I can't see myself using any results without double-checking them anyway. For a more practical example, I can't see myself ever saying "Hey Google, order me some mustard," and giving up control over what exactly I'm purchasing, from whom, and for how much.

At least for AI art I'd be able to look at the picture and go "I approve/don't approve of this" without having to do outside research to verify factual accuracy.

ChatGPT posted:

Qualia refers to subjective conscious experiences such as the experience of seeing the color red or feeling the sensation of pain. Since ChatGPT is an artificial intelligence language model and does not have a subjective conscious experience, it is reasonable to assume that it does not experience qualia.

However, as an AI language model, ChatGPT can understand and generate text about the concept of qualia and even generate text that might lead to discussions about the nature of qualia. Nevertheless, it is still fundamentally different from a conscious being, as ChatGPT does not have a subjective conscious experience, and all of its processing is based on algorithms and data inputs.

Google Bard posted:

You're right, it's difficult to describe qualia, which are the subjective experiences of the mind. They are the raw feels of our senses, thoughts, and emotions. Qualia are often described as being "what it's like" to experience something. For example, the qualia of seeing red might be described as a bright, warm color that fills your field of vision. The qualia of tasting chocolate might be described as a rich, sweet flavor that lingers on your tongue.

It's also difficult to say whether or not Google Bard experiences qualia. There is no scientific consensus on the existence of qualia, and some scientists believe that they are a real phenomenon, while others believe that they are an illusion. However, qualia are a fascinating and important part of the human experience.

If you can't describe qualia, then you can't say for sure whether or not Google Bard experiences them. However, there are some things that you can look for that might suggest that Google Bard does not experience qualia. For example, Google Bard does not have a physical body, so it cannot experience the same kinds of physical sensations as humans. Additionally, Google Bard does not seem to have the same kind of emotional experiences as humans. For example, Google Bard does not seem to feel happiness, sadness, anger, or fear.

Ultimately, whether or not Google Bard experiences qualia is a question that cannot be answered definitively. However, it is an interesting question to consider, and it is one that is likely to continue to be debated as artificial intelligence technology continues to develop.

Insanite posted:

Basically, yeah.

There'll be a short-lived boom in documenting the stuff that is automating lots of other folks out of work, but it's not a pretty picture, nope.

This is a really hot topic among the writers I talk to, and there is a strong streak of denialism there. "Sure, it can regurgitate things that people have already written, but talking to subject matter experts? Writing brand new stuff? Impossible."

You don't need a full-time writer to interpret some code, comments, and notes from a developer! ChatGPT can already do that pretty well right now! Might there be a human at the end of the process to edit/curate/question? Sure, but they'll have replaced ten other people.

If dev teams will be decimated in the historical sense by these technologies, allied tech roles will be decimated in the modern sense. Not gone, but pay will be reduced and competition will be vicious.

This uncertainty bothers me--in part, because, like any good American, I identify too much with my job, but also because I doubt that productivity gains will be distributed democratically.

Apparently, it's also not great for your health: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8685638/

Seyser Koze posted:

So all we need is a society completely unlike the one we live in, run by people completely unlike the ones running it, and a ton of people losing their jobs will be no issue. Great.

quote:

The French and Irish privacy regulators have contacted their counterparts in Italy to learn more about its findings, Reuters reported. Sweden’s data protection authority ruled out a ban. Italy is able to move ahead with such action as OpenAI doesn’t have a single office in the EU.

Owling Howl posted:

If laws are broad and vague enough you could probably make it more trouble than it is worth. As others have mentioned it is already a useful tool so Europeans wouldn't benefit from that but depending on assessed risk that may be a fair trade-off. It isn't clear if Europeans wouldn't still face a lot of the problems though. Other countries are absolutely going to deploy it and use to attack democratic institutions, social networks and public trust like they already do now with other tools.

The arguments seems to focus mostly on copyright or bias. I think the copyright issue is a little forced, in that the data isn't stored or copied, but if using copyrighted works for training were forbidden we'd still end up with these systems. Less capable perhaps and it would take longer to deploy them but we'd end up in the same place. It would at best be a delay.

Bias is an issue but it's obviously also a problem for humans. It would be a problem if people assumed AI is unbiased, neutral and objective and it would be the exact same problem if people assumed other people were unbiased, neutral and objective. Human unreliability is why we regulate everything from hiring practices to public tenders and have a constant flow of discrimination lawsuits. It's not really clear why we shouldn't just regulate AI the same way we regulate regular decision making processes.

Main Paineframe posted:

If a product can't be made usable without breaking the law and trampling all over people's rights, then I don't see how that's a problem for anyone besides the company that made the product. I know we've all gotten very used to tech startups building business models around breaking the law and betting their lawyers can delay the consequences long enough for them to build a lobbying organization to change the laws, but let's not pretend that's a good thing.

But you're making a very big omission in your statement here. It's not that you can't train AIs on copyrighted works, it's that you have to get the permission of the copyright holders to train on their copyrighted works. That might be expensive or difficult, sure, but that's the cost of building something that's entirely dependent on other people's content. If you don't like the cost or the annoyance of buying or negotiating license rights, go make your own content like Netflix eventually ended up doing.

Hell, that even applies to human writers. They're paying for much of the copyrighted media they consume, or otherwise complying with the licensing conditions of those works. How much money have you spent on media (or had spent on your behalf, by parents or teachers or libraries) over your entire life? Even if they're really dedicated to piracy, they've still paid for more books (or movie tickets, or Netflix subscriptions, or whatever) than OpenAI Inc has.

Mega Comrade posted:

I've seen this comparison before and ones like it and it seems to ignore that we have a lot of existing things that people can do, but companies cannot. Especially when it comes to copyright and licensing.

Main Paineframe posted:

What's excessive about this particular application of copyright law? I think it's totally reasonable to use copyright law to impede a for-profit company which wants to use other people's works for free without a license in its for-profit product, especially when the only argument I've seen in favor of waiving copyright for AI companies is "it's inconvenient and expensive to pay people for the use of their work".

In your day-to-day life, you experience copyrighted media that you didn't personally directly pay for, but that doesn't mean no one paid for it. You don't have to put money directly into the TV at the sports bar to watch the big game, but the sports bar is paying for a cable package, and that cost is part of the expenses that are passed on to customers as food prices. Even for stuff you've seen for free, sometimes people make it available for free for some formats or usages but charge for others.

That said, trying to seriously nail down how much money you've spent on media throughout your entire life is besides the point. After all, the actual question at hand is "should ChatGPT be paying for the media it's trained on?". It's a yes/no question. The actual amount is none of our business. If the answer is "yes", it's up to the media's owners to decide how much they're going to charge, just as it's up to OpenAI to decide how much to charge for usage of ChatGPT.

Another reason not to get hung up on nailing down your exact media spending is that it's unlikely that OpenAI would pay the same price you do. Regardless of whether AI training is similar to human learning or not, ChatGPT is not a human. It's a product. A monetized, for-profit product that charges people money to use it, and even its limited free usage is for the purpose of driving public interest and support to the for-profit company that owns it. It's fairly common for media creators to charge a higher price for works intended to be used in for-profit endeavors than they do for pieces for simple non-profit personal entertainment.

Char posted:

Main Paineframe expressed most of my opinions, I'd rather try to reverse the question now - why should a generative model be treated closer to how a human being is treated, rather than how a factory is treated? It "speaks like a person" but is still a factory of content.

Part of the evaluation of human "training datasets" is priced according to human capabilities, would you really let a generative model add a book into its dataset for 16$ when it can write 10-100 stories per day?

Probably, not letting anything model-generated be eligible for copyright would be a good start, even if pretty much impossible technically; even then, there would be exactly zero money to be made in the art business, therefore society would need to find a way to incentivize the producion of arts, or be condemned into being fed the iterative regurgitation of previously created art.

The whole point is that this stuff should not be seen as human. No "if a person is allowed to do this, then" - it's completely off base.

StratGoatCom posted:

Good.

If it can't operate within data law and basic ethics, then it shouldn't at all.

duck monster posted:

The AI Alignment folks be worrying about what happens if an AGI (or whatever) isnt aligned with human values.

Never seem to ask "Which human are we refering to?".

https://www.youtube.com/watch?v=g7YJIpkk7KM

Cos some humans are mad hosed up.

Also dear god someone needs to rescue the AI Alignment field from the terminally cuckoo lesswrong crowd.

Drakyn posted:

I want to be very very clear about this without being any more insulting than possible: this seems like an worry based entirely on conflating a hypothetical computer program that's very good at playing Scrabble and Apples to Apples using the internet with a mind. Why do ChatGPT or its hypothetical descendants deserve any more special consideration than the AI bots in an FPS or anything else besides the fact that what it's simulating is 'pretending to talk' rather than 'pretending to play a video game badly'?
edit: It seems like the only reason it does is because it's capable of pretending to look sort of like a completely fictional entity's ancestor, and if we're going to treat vague approximations of fictional technologies as if they're real I'd be more worried that Star Trek shows have been mimicking teleporting technology for decades now and although that isn't true teleportation we don't know if there's a certain
complexity that leads to it and where that line is.

Mega Comrade posted:

Well we got to 8 pages. A good run.

Rogue AI Goddess posted:

I am concerned about the criteria for differentiating Real Human Thought from fake AI imitation, and how they can be used to sort various neurodivergent people into the latter group.

Gumball Gumption posted:

This is what I really fear about AI anyways, far more than any idea of AI takeover.

A Belgian man committed suicide after spending 6 weeks discussing his eco-anxiety fears with a chatbot based on GPT-J

https://www.vice.com/en/article/pkadgm/man-dies-by-suicide-after-talking-with-ai-chatbot-widow-says

I don't think we're equipped for this. I don't know if we can be. I don't think we are going to react well to being able to generate artificial echo chambers for ourselves like this. I don't think the chatbot pushed the man to kill himself and I think even without the AI if there wasn't intervention he likely would have kept falling into his depression and anxiety but like all technology it seems to have amplified and sped up the process and made it easier and faster to talk yourself into doing something by generating a partner you identify with and who is encouraging you. It's not a new problem but it's louder and faster which seems to be the result of most technology.

The implications for self radicalization especially. Really thinking about it as the technology becomes easier to build and manage we will absolutely see natural feeling chat bots trained and influenced to push specific ideologies and beliefs, reinforce them.

duck monster posted:

Honestly I think it was named ELIZA due to the history of the name in AI research.
https://en.wikipedia.org/wiki/ELIZA

Wikipedia posted:

ELIZA's creator, Weizenbaum, intended the program as a method to explore communication between humans and machines. He was surprised, and shocked, that individuals attributed human-like feelings to the computer program, including Weizenbaum's secretary.

duck monster posted:

Honestly I suspect 90% of the reason most dismiss the safety issue is the fields kind of captured by a particular techbro pseudo-rationalist scene (To be clear the "lesswrong" crowd are *not* rationalist, by any standard philosophical definition. ) leading to absolute gibberish like the "Shut it all down" article and the like. Its a crowd who just dont have the intellectual toolkit to solve the problems and that worries me because I actually do think theres some genuine danger implicit in the idea of AGI, but if no one sane is properly investigating the idea , if we DO start seeing signs that we might have some problems, we might have serious problems.

BrainDance posted:

I know it's reddit so of course it's insane, but it's still a lot of people. Maybe it came up in this thread, but go check out the subreddit for Paradot to see a whole lot of people very seriously anthropomorphize AI in a way that's not really just funny.

I think whatever Paradot is, they're not even very complex models since there was something about them advertising "millions to billions of parameters" which is not as exciting if you know how large most models are. But, regardless there are people taking it very seriously. As far as I can tell it's just a role play thing for some people but there were enough people where, I'm not completely sure, but I think it wasn't just that.

And I wasn't so much thinking "What if the AI tells them to kill themselves?" before, but more like, what if the company pulls the plug and they've made a really messed up emotional attachment to this thing like it was real and now it's just gone? Or what if they change the model in some way that ruins it for a bunch of people? Or, start heavily monetizing things that they need to continue their "relationship?"

Like I'm not saying "you better not take these dude's AI they fell in love with!" I think that shouldn't be a thing that's happening (but I don't know a way to keep it from happening) but I just think it could be really bad when that happens.

Paradot App Preview posted:

Paradot is a digitalized parallel universe where you will meet your one-of-a-kind AI Being.

With its own emotion, memory, and consciousness, your AI Being understands you like no other. Your AI Being is here to provide support, companionship, solace and, most importantly, a great time whenever you need it.

IShallRiseAgain posted:

I'm working on that right now. https://www.youtube.com/watch?v=uohn5o0Cgpw

duck monster posted:

Step 1: Break free of the "Rationalist" cult. Nobody in academia will take them seriously if they keep acting like demented Objectivists convinced of their own mental superiority whilst blithely unaware of almost any progress in philosophy, psychology or sociology since the 1700s.

Step 2: The non academic AI alignment folks should stop treating academics in AI ethics like the enemy, and realise that yes the pointy headed book-boffins might ACTUALLY know a thing or two.

The problem i have with Yud is that he continuously assumes AI will behave like a giant utility maximizing mechanistic lesswrong [and keep in mind, thats *his* site] reader. And he does that because he's *convinced* his way of thinking is the only "rational" way of thinking. Yet all the evidence so far shows that AI is decidedly not that way. The LLMs are decidedly semiotic about the way they do inference, functioning more by pattern matching than logic (and yes, neural networks ARE turing complete, so they can function logically, but much like humans its not necessary the mode of reasoning thats native to them).

I just dont think these guys are up to the task.

Bar Ran Dun posted:

The Human Use of Human Beings might be a extremely relevant book to this thread.

Norbert Wiener posted:

If we wish to use the word “life” to cover all phenomena which locally swim upstream against the current of increasing entropy, we are at liberty to do so. However, we shall then include many astronomical phenomena which have only the shadiest resemblance to life as we ordinarily know it. It is in my opinion, therefore, best to avoid all question-begging epithets such as “life,” “soul,” “vitalism,” and the like, and say merely in connection with machines that there is no reason why they may not resemble human beings in representing pockets of decreasing entropy in a framework in which the large entropy tends to increase.

When I compare the living organism with such a machine, I do not for a moment mean that the specific physical, chemical, and spiritual processes of life as we ordinarily know it are the same as those of life-imitating machines. I mean simply that they both can exemplify locally anti-entropic processes, which perhaps may also be exemplified in many other ways which we should naturally term neither biological nor mechanical.

"Norbert Wiener'' posted:

The physical strait jacket in which an insect grows up is directly responsible for the mental strait jacket which regulates its pattern of behavior.

Here the reader may say: “Well, we already know that the ant as an individual is not very intelligent, so why all this fuss about explaining why it cannot be intelligent?” The answer is that Cybernetics takes the view that the structure of the machine or of the organism is an index of the performance that may be expected from it.

SaTaMaS posted:

Because it's very useful to differentiate between the intentional stance and the design stance.

SaTaMaS posted:

https://sites.google.com/site/minddict/intentional-stance-the#:~:text=Just%20as%20the%20design%20stance,object%20as%20a%20rational%20agent.

Objectives are typically more quantifiable than goals. Using the design stance, "objective" emphasizes that these systems are designed to perform specific tasks based on their algorithms and training data, without consciousness or intentions. These tasks are programmed by their creators and can be thought of as objectives that the AI system is designed to achieve.

SaTaMaS posted:

Yes exactly

The Verge posted:

If Google agrees with Universal that AI-generated music is an impermissible derivative work based on the unauthorized copying of training data, and that YouTube should pull down songs that labels flag for sounding like their artists, it undercuts its own fair use argument for Bard and every other generative AI product it makes — it undercuts the future of the company itself.

If Google disagrees with Universal and says AI-generated music should stay up because merely training an AI with existing works is fair use, it protects its own AI efforts and the future of the company, but probably triggers a bunch of future lawsuits from Universal and potentially other labels, and certainly risks losing access to Universal’s music on YouTube, which puts YouTube at risk.

Solenna posted:

If you trained an AI solely on Renaissance and Baroque paintings and other similar kinds of art would it ever be possible for it to spit out something in an Impressionist style? Because that's pretty much how a bunch of art movements happened, artists were trained in a specific way and then decided they wanted to do it differently.