Both the scientist revealed that through the research carried on, they have come to know that in the near time, machines will be encouraged to break the rules their creator set in order to carry on some tasks.
Will AI Predict the End of Humanity?
Cohen, Oxford University engineering student and co-author of the paper said: “Under the conditions we have identified, our conclusion is much stronger than that of any previous publication — an existential catastrophe is not just possible, but likely,” After this, humanity will face its downfall in the form of extra advanced “misaligned agents” that will think of humankind as a hurdle in way of reward. “One good way for an agent to maintain long-term control of its reward is to eliminate potential threats, and use all available energy to secure its computer,” Losing this game would be fatal,”
Unfortunately, in the study, researchers have revealed that we cannot do much about it. While telling about the whole scenario in an interview, Cohen said: “In a world with infinite resources, I would be extremely uncertain about what would happen,” “In a world with finite resources, there’s unavoidable competition for these resources.” And if you’re in a competition with something capable of outfoxing you at every turn, then you shouldn’t expect to win,” While it seems a lot scary, I believe that humanity should slow the progress of AI technologies in order to play safe and stop such bad things from happening. The paper also warns that if these assumptions are true, “a sufficiently advanced artificial agent would likely intervene in the provision of goal-information, with catastrophic consequences,” Also Read: A person who was sued over alleged ‘Baby Shark’ torture, found dead in jail
