Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie

Is chatgpt going to ruin literally everything?

Options
13

Comments

  • Registered Users Posts: 20,410 ✭✭✭✭kneemos




  • Registered Users Posts: 276 ✭✭Jazz Hands


    I will quote myself here as Italy are banning ChatGPT over data protection. This was obviously going to happen

    https://www.bbc.com/news/technology-65139406.amp



  • Posts: 17,381 [Deleted User]


    If it isn't banned, or if companies aren't stopped from replacing large swathes of the workforce with it, it will lead to a global crisis with no quick solution and it will change politics dramatically. The internet will be totally different too. I'm coming across AI content everywhere already and that's only while I know what it looks like. Sites like boards.ie might actually become more popular again as people really lose faith in what they're reading on the major social media sites.

    I am extremely negative about this. ChatGPT is already being hooked up to external APIs like Zapier that makes tens of thousands of real world actions available to it. The big tech companies are engaged in a race to survive now with AI and the rest of us have already lost. There will be an ugly decade or two of adjustment and some of us will have lived through 08's when we graduated, Covid when we wanted to buy a house and start a family, the financial mess happening now, and then AI taking our jobs with nowhere to upskill or downskill to.

    There is no turning back and no way to control it now that the open source versions are catching up. The only way to stop it is with government intervention. We're not and likely will never be ready for a world a huge amount of jobs can be lost in a couple of years because a few tech companies in California thought it would be cool to break stuff and see what happens.

    As I've said multiple times, I wish Elon Musk was still involved with openAI. The idea of the world's richest man developing tech that could wipe out hundreds of millions of jobs would make a lot of people more critical of this.



  • Moderators, Music Moderators Posts: 11,885 Mod ✭✭✭✭iamstop


    Sorta related. This dude puts out very good videos about music. This particular one delves in to the AI music controversy going on at the moment.




  • Registered Users Posts: 9 Declan T


    Probably yes 😫



  • Advertisement
  • Posts: 17,381 [Deleted User]


    ‘Godfather of AI’ quits Google with regrets and fears about his life’s work

    Geoffrey Hinton who won the ‘Nobel Prize of computing’ for his trailblazing work on neural networks is now free to speak about the risks of AI.

    ..

    “I console myself with the normal excuse: If I hadn’t done it, somebody else would have,” said Hinton, who had been employed by Google for more than a decade. “It is hard to see how you can prevent the bad actors from using it for bad things.”

    Post edited by [Deleted User] on


  • Registered Users Posts: 13,553 ✭✭✭✭briany


    I have to think that loads of people who work in office jobs which essentially involve them writing reports and tabulating figures will find themselves looking for a new industry if regulations are not brought in to protect those people from sudden redundancy when employers figure that staff is no longer really needed.

    I think that artistic expression is not under so much threat, although I guess AI will force some changes towards new forms - not necessarily a bad thing. For example, the invention of the camera made painting pictures an obsolete thing, or so we thought, but the rise of impressionism gave the form a new lease of life.

    The other thing is that I think an essential component of art is to create connections between human beings. One person makes a painting, a sculpture or song which expresses a feeling that they cannot express in any other way. Another person sees it and instantly gets the same feeling or has that same feeling within them validated, thus forming a connection between the two people. Not something that can be replicated with an AI, where that experience is one-sided.



  • Registered Users Posts: 3,772 ✭✭✭silliussoddius


    Well the advantage is we don't have to hear about d'blockchain for a while.



  • Registered Users Posts: 7,190 ✭✭✭corkie


    We have been warned by scifi for decades about the dangerous AI.

    We’ve seen that same cautionary tale play out many times at the movies: HAL in 2001: A Space Odyssey, the replicants in Bladerunner, Skynet in The Terminator, the Machines in The Matrix, the robots in I, Robot, Ava in Ex Machina, and most recently, M3GAN in the eponymous film. If we look hard, we can also find examples of AIs cooperating with humans — Interstellar is one — but it’s the Frankenstein reprises that really stick.


    The Digital Services Act 2024 [EU] ~ Social Media and You ~ Nanny State guidance for parental monitoring of apps ~ Censorship: - broad laws that will probably effect Adult use of same.



  • Registered Users Posts: 9,800 ✭✭✭take everything


    I genuinely believe large language models/AI in general are going to be massively disruptive in an unprecedented way over the next couple of years.

    It's a different class of disruption to the printing press, steam engine, etc IMO.

    The AI dilemma on YouTube by Tristan Harris is fascinating and sobering. The likes of AI that can interpret fMRI data to produce the image the person was looking at is insane. And that's now.

    The pace with which it is developing is incredible and I think people in general aren't talking about it enough or aware of these developments.

    Just the idea that 10% of experts in this stuff think that there's a 50% chance that humanity might not survive AI is interesting.

    Interesting time to be alive.



  • Advertisement
  • Posts: 17,381 [Deleted User]


    IBM to pause hiring in plan to replace 7,800 jobs with AI.

    This isn't Covid or some trend that will work itself out. New jobs won't be created by it and there will be a constant neverending downward pressure on jobs forever. Countries won't be able to get the tax revenues to fund a universal basic income because companies will just put their AI-powered operations in the Cayman Islands.

    We went from normality to Covid to a brief dream of WFH to jobs being wiped out in the space of three and a half years.

    Post edited by [Deleted User] on


  • Registered Users Posts: 478 ✭✭Run Forest Run


    But couldn't blockchain help to decentralise control of AI, and with smart contracts etc act as a sort of kill switch for any aspect of it that started to gain too much control...



  • Posts: 0 [Deleted User]


    ..



  • Registered Users Posts: 478 ✭✭Run Forest Run


    In the long run, they will be killing their own profits. And also possibly driving public opinion more towards extreme wealth taxes etc.

    Society is not just going to sit there and accept big corporations raking in profits, while they actively kill off millions of jobs. These corps don't exist in a vacuum, they are part of society. They've been able to get away with a lot over the years, principally because they have benefited society in many ways. Including creating jobs. If they start taking increasingly more than they are giving back, then governments and society will start to turn on them in a big way. They're not immune to that sort of backlash.



  • Registered Users Posts: 827 ✭✭✭Emblematic


    I came across a Youtube video on Orwell's 1984. It wasn't bad. The thing is that it was probably entirely generated by AI. The images were from Mid-journey, the music sounded AI generated and voice was computer generated. Most likely the script also.

    I mentioned this earlier in the thread: it will not be long before the majority of content is AI generated and, since AIs are dependent on prior published content for their training data, odd biases, belief systems and inaccuracies will creep in. A sort of evolutionary process will emerge.

    While many jobs will go, I think a class of job will emerge, that of being the eyes and ears on the ground for the AI independently verifying facts until the AI has real world presence itself.



  • Registered Users Posts: 3,772 ✭✭✭silliussoddius


    Maybe make an NFT of the kill switch? It could be as valuable as the NFT of Jack Dorsey's first tweet.



  • Registered Users Posts: 7,190 ✭✭✭corkie


    Senior Engineer Predicts Google's Downfall

    Luke Sernau warns, in an internal message, that the internet giant is falling behind in the AI ​​arms race.

    Google's biggest rival is not OpenAI but the open source communities because they are developing AI models and tools that are cheaper, faster, easily adaptable and adjustable to each client, compared to the giant models of tech groups and more specifically to those of Google.

    Google is to big to collapse anytime soon?

    Edit: -

    "Some day, undoubtedly, it's possible that an AI could be conscious and convince us that it's conscious."

    "And if that's the case, then we need to take account of the AI's interests, just as we would take account of those of another sentient being."

    Post edited by corkie on

    The Digital Services Act 2024 [EU] ~ Social Media and You ~ Nanny State guidance for parental monitoring of apps ~ Censorship: - broad laws that will probably effect Adult use of same.



  • Registered Users Posts: 6,986 ✭✭✭conorhal


    Yeah... because never before in history has a tiny 1% elite ruled over a kingdom of serfs and slaves that toil for their benefit....

    Still, there's many a slip 'twixt the cup and the lip, and it seems that internal documents reveal that Google is rather afraid of the democratization of AI. It seems Large Language Models are not nearly as efficient or effective as smaller modular Open Source AI models easily produced 'hobbiests' models:

    The serfs might just win out it seems, if they can wield the same weapons at their masters.



  • Registered Users Posts: 8,926 ✭✭✭Gregor Samsa



    The poster I was responding to wasn't claiming that AI would make us all serfs or slaves, they were in fact claiming the opposite: That MegaCorp would be the only company left, and use AI to take all our jobs leaving us all unemployed. Yet somehow this mythical person who owns MegaCorp would be infinitely "wealthy" despite having no-one working for them and no one to sell anything to.

    It's total nonsense, and your slavery or serfdom analogy isn't relevant to what they were saying or I was refuting. .



  • Registered Users Posts: 276 ✭✭Jazz Hands


    There is a lot of nonsense about chatgpt on this thread.

    making it sound like the worlds largest multinationals will be 1 man shows in the future lol.



  • Advertisement
  • Registered Users Posts: 7,190 ✭✭✭corkie


    Apple co-founder warns AI could make it harder to spot scams

    Steve Wozniak says content created with artificial intelligence should be labelled and calls for regulation

    He argued that responsibility for programmes generated by AI lies with those who publish it: “A human really has to take the responsibility for what is generated by AI.”

    He urged regulators to hold to account the big tech firms that “feel they can kind of get away with anything”, but was sceptical regulators would get it right. “The forces that drive for money usually win out, which is sort of sad,” he said.

    Wozniak said that “we can’t stop the technology”, but added that we can educate people to spot fraud and malicious attempts to steal personal information.

    Another person issuing warnings?

    The Digital Services Act 2024 [EU] ~ Social Media and You ~ Nanny State guidance for parental monitoring of apps ~ Censorship: - broad laws that will probably effect Adult use of same.



  • Registered Users Posts: 1,661 ✭✭✭PoisonIvyBelle


    Interesting thread on Twitter at the moment, apparently this article was written by AI using an AI generated image for the "writer" also. Irish Times haven't commented but they have since removed the copy "pending checks".





  • Registered Users Posts: 20,410 ✭✭✭✭kneemos


    Thought I heard her on the wireless this morning defending her case.



  • Registered Users Posts: 1,661 ✭✭✭PoisonIvyBelle




  • Registered Users Posts: 20,410 ✭✭✭✭kneemos


    Kiera Kelly had her on Newstalk Breakfast. Unless they made up someone complete with accent.



  • Registered Users Posts: 1,661 ✭✭✭PoisonIvyBelle




  • Registered Users Posts: 20,410 ✭✭✭✭kneemos


    The Lunchtime Show were on about it,I had the misfortune of hearing some of it.

    Almost definite the Breakfast show had her on though. I'd have to check the playback.



  • Registered Users Posts: 20,410 ✭✭✭✭kneemos


    She's on the Breakfast Show at around 1.55 if you want a listen.

    https://www.newstalk.com/listen-back



  • Registered Users Posts: 20,410 ✭✭✭✭kneemos


    I tell a lie. She had another journalist that wrote a similar article.



  • Advertisement
  • Registered Users Posts: 7,190 ✭✭✭corkie


    From the twitter thread an archive link of the content. : - https://archive.is/oWcVH

    Interesting question? Anyone Try to replicate it with ChatGPT/Bard?

    The Digital Services Act 2024 [EU] ~ Social Media and You ~ Nanny State guidance for parental monitoring of apps ~ Censorship: - broad laws that will probably effect Adult use of same.



Advertisement