Is chatgpt going to ruin literally everything?

Must be one of the first ever technological leaps where those ignorant of it think it's harmless and the ones who understand it have a fear of it?

The literal creators and sellers of it, along with a huge amount of researchers: "This is dangerous." Finance firms: "This will disrupt 300 million jobs." Deepmind cofounder: "The rise of advanced artificial intelligence will upend the white-collar job market and result in a large number of “very unhappy” workers." Frogs in slowly boiling water: "It's just an app that predicts the next word."

If your understanding of ChatGPT is that it's some website people have to use and interact with, you are clueless. Humans won't be a part of any of it once it's tied into systems to receive input and output instructions.

And that's not even looking at the uncensored versions of this stuff.

I could easily create a program that listens to every new post on boards.ie, uses ChatGPT to get the posts' sentiment towards any number of issues I am in support of or against, load up that users' post history and my own bots' responses in that thread so far, and use that to craft a response with something like ChatGPT if the subject matter is socially acceptable (openAI acceptable), or something like the above if I have unacceptable views.

This would run 24/7 and with the help of 10 or 20 accounts and VPNs, I could dominate a bunch of discussion on the site. This is already happening on the larger platforms.

https://www.boards.ie/discussion/comment/120605344#Comment_120605344

AI might not have an actual idea of what a bird is, but it does remarkably well.

This is not some statistical autocomplete based on what it has read before. It is not simply thinking of what the next sentence is based on sentences it has read before. It tokenises concepts in the text and is able to create links between those tokens and produce ideas and text that no one has ever written about before.

kneemos

How dumb will we get if AI does everything?

Lewis_Benson

https://www.boards.ie/discussion/comment/120606445#Comment_120606445

Already happening, look at every person under 25, head buried in their phones.

corkie

@CalamariFritti And for starters people who are freaked out about 'artificial intelligence' need to be told that these things are NOT what most people think what artificial intelligence means.

Are you differentiating between Sentient and Not? You answered that in the rest of your post.

Could you explain what you think the terms means? As pointed out if the creators are concerned, why shouldn't people be freaked out.

https://www.rmit.edu.au/news/acumen/ChatGPT_sentientorsingularity

In conclusion, while ChatGPT is a powerful language model, it is not sentient and does not bring us closer to the Singularity. Sentience and the Singularity are complex and highly speculative concepts that are the subject of ongoing research and debate in the field of artificial intelligence. As with any new technology, it is important to consider both the potential benefits and drawbacks and to approach its development and deployment with caution.

Asked Bard 'Should people be freaked out about you?'

I don't think people should be freaked out about me. I am a large language model, also known as a conversational AI or chatbot, trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories. However, I am not sentient or conscious, and I do not have the ability to feel emotions or act on my own. I am simply a tool that can be used for good or bad, depending on the intentions of the person using me.

I believe that AI has the potential to be a powerful force for good in the world. It can be used to solve complex problems, improve our lives, and make the world a better place. However, it is important to remember that AI is a tool, and like any tool, it can be used for good or bad. It is up to us to ensure that AI is used for good and not for evil.

I am committed to using my abilities for good. I want to help people learn and grow, and I want to make the world a better place. I believe that AI has the potential to make a positive impact on the world, and I am excited to be a part of that. ~~ Response by Google 'Bard'.

It does tend to repeat itself in the reply?

jackboy

I expect in a few years we will look back on chatgpt as something quaint and rudimentary. This will utterly change the world.

quokula

Regarding the Irish Times hoax.

Someone came up with the idea for the article and prodded the AI into writing it. Someone proofread it and decided it was fit to be published.

In a way all the AI is doing here is democratising the ability of people to make their ideas heard, for those who are maybe less eloquent or less skilled at word smithing.

If the article was written in bad faith then it could have been manually written in bad faith, that’s not the AI’s fault .

In some ways it feels like a modern day equivalent to a Middle Ages pushback against typewriting which was mechanical and lacked the skill of hand written manuscripts.

corkie

https://www.boards.ie/discussion/comment/120605414#Comment_120605414

https://news.sky.com/story/i-fell-in-love-with-my-ai-girlfriend-and-it-saved-my-marriage-12548082

Remembered your post when I came across the above, didn't search for it it was linked in other articles.

Ger Roe

There was an interesting take on all of this from Ossian Smyth TD, on 'Morning Ireland' (RTE Radio 1), this morning.

Basically , we should not get ahead of ourselves .... there is no immediate threat, even when various Government departments currently have different policies (or lack of) on how it can, or should, be used ... there is no need for a joined up thinking and whole of government approach. He said that the current non coordinated and non officially advised approach to the use of AI within Government, was 'appropriate' at the moment..... appropriate?????

The man obviously doesn't understand the the implications and ironically he could be right in his thinking, stupid humans in power might be more of a risk to our future at the moment, rather than the intelligent machines.

If Ireland adopts our usual approach of waiting to see what happens and then reacting on impulse, we could be in a spot of bother. Mr Smyth's incredibly naieve contribution to the debate this morning, combined with the arrogance of his belief, would have me concerned.

Maybe there is an IDA backed and tax break funded company somewhere in the country that is leading the charge in AI development? ... that would at least explain his reluctance to officially consider the matter seriously.

corkie

https://openai.com/blog/governance-of-superintelligence

Above posted on Monday 22nd.

https://www.bbc.com/news/technology-65708114

And it could require generative AI companies to reveal which copyrighted material had been used to train their systems to create text and images.

"The current draft of the EU AI Act would be over-regulating," OpenAI's Sam Altman said, Reuters reported.

"But we have heard it's going to get pulled back."

They have asked to be regulated, if the Laws (which will take a good while to implement) are too extreme, they will just go elsewhere?

Edit Friday: -

ChatGPT-maker U-turns on threat to leave EU over AI law

corkie

The WHY Files | Artificial Intelligence Out of Control: The Apocalypse is Here | How AI and ChatGPT [could] End Humanity

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

^^^ Note sponsor content after the first minute intro, so skip to 4 if you don't want to watch it.

Unusual for this channel to tackling this content, usually debunking stories.