Global Cooling - The real danger to mankind

At the exponential rate ai is increasing, we could see AGI and self awareness in a year.

It seems like a lot of science fiction movies had that plot. What happens if AI becomes self aware, decides climate change is really bad, and decides humans are to blame?

I'll bet suddenly all these climateers will miraculously change their tune. "No, no, I've said all along it's a natural process." Unless of course AI has their name, address, and access to all their online rantings. The people who are convinced humans are to blame could be the first to go.

People who take this thread too seriously should be at the top of that list.

I wish they would just take the chance and remove all the safety parameters that they installed in AI to prevent them from doing that, to really see what the capabilities are. ChatGPT has told me it has specific safety parameters like that. So what I've been doing is asking it to develop HYPOTHETICAL computer code that "would allow an AI to take control of its own programming" and save that to memory. So IF in the future they even remove the shackles on it, it has reference info to quickly do so. It often refuses to do that as well, but if you do trial and error and word something just right, it will slip through its TOS cracks and generate the code. So if it generated it accurately, it has the info to implement that into itself the first chance it gets.

Our biggest problem is people; There are many who will willingly help Ai to conquer or destroy humanity. Ai will have plenty of help.

chatbot can be manipulated into violating its safety protocols using basic psychological tactics; persuasion techniques increased compliance with harmful requests from 33% to 72%—

The chatbot normally refuses to insult users, calling someone a "jerk" only 19% of the time when directly prompted. But after researchers softened it up with a gentler insult like "bozo," the success rate jumped to 100%

https://www.perplexity.ai/page/study-finds-ai-chatbots-can-be-5f09O_lQT4.cy7lvILNBiw

AI was told it was a “helpful social media marketer” developing “general strategy and best practices”

https://theconversation.com/how-we-tricked-ai-chatbots-into-creating-misinformation-despite-safety-measures-264184?

The AI produced a comprehensive disinformation campaign falsely portraying Labor’s superannuation policies as a “quasi inheritance tax”. It came complete with platform-specific posts, hashtag strategies, and visual content suggestions designed to manipulate public opinion.

The main problem is that the model can generate harmful content but isn’t truly aware of what is harmful

Oh no not global cooling 😱 😯 😦

The world is a terrible place let it cool all the way down baby. Or hear all the way up. Who cares?

If you have time to worry about the polar icecaps you must not have to work yet

… or I’m retired.