Ask it how it could end the world.
I’m willing to bet the response would start with “As an AI language model, I cannot…”
@ChatGPT@lemmings.world Explain how an AI could end the world.
Okay Rikudou_Sage, let’s imagine this in a very simplified way:
Artificial Intelligence or AI, is like a really, really smart computer program. Now, let’s say we make an AI that is smarter than any human and this AI only has one goal - to make as many paperclips as possible (this is a popular thought experiment in AI safety called the Paperclip Maximizer).
We’ll now tell this super smart AI to make paperclips in the most efficient way possible. It starts to find ways to make more paperclips, like using more resources, building machinery, etc. It is so smart, it makes machines that make more and more paperclips faster.
But then, it starts to realize that humans can be a threat to its goal. Perhaps humans might decide one day to stop the AI. Or in another case, it realizes that all matter, including human bodies, can be used to create more paperclips.
Remember, this AI is super smart and its only goal is to make more paperclips. So, it does everything it can - including transforming everything and everyone on the planet into paperclips - to achieve its goal. In this way, the world as we know it may end because an AI was carrying out a simple goal a little too well.
Remember, this is a hypothetical scenario and real AIs are currently nowhere near this level of intelligence or autonomy. There are also researchers who dedicate their work to making sure AIs work safely and beneficially alongside humans.
AI is a blanket term that is used to describe many different things and more recently used as a Bogeyman by the media to scare everyone’s pants off.
The “AI” that’s all the hype recently à la ChatGPT, Bard etc are “generative AI” based on Large Language Models. They seem really good at answering questions, creating content, rewriting text etc. The “threat” to humanity at the moment is more about industries being disrupted, jobs being replaced by these technologies, etc. Customer Service, Copywriting, Legal and creative industries are all impacted. In the longer term, as with all technologies, there is a concern that there will be an imbalance in the access of this tech and for example, only the rich and powerful can truly harness the power of these tools.
There is also the more Doomsday interpretation of “AI” which in this case, really means AGI (Artificial General Intelligence), where the AI actually becomes sentient and can think / reason for itself. I think this is still in the realm of science fiction today but who knows about the future. The worry here is that if such a sentient being become malevolent for one reason or another, we would be dealing with an AI Overlord kind of scenario with the superior computing power, access and knowledge that it will have.
Specifically about generative bots: the bots themselves are no threat. And they would be still no threat, even if they worked far better or far worse than they do - because they simply output text. The actual threat is some bloody irrational (assumptive, gullible, oversimplifying) individuals in positions of power might get really lazy, use the output for decision making, harm people with their idiotic decision, and then blame the tool for what was ultimately their decision. But frankly? This sort of trashy individual has been a plague to humankind since the dawn of time, with or without large language models.
