- Humanity will meet its end.
- Article published AI Magazine by researchers.
- Machines would be encouraged to defy the constraints their creator.
Superintelligent AI will soon expose the demise of humanity, according to Oxford and Google Deepmind researchers who have studied the subject. More researchers have foreseen this possibility. An article on this topic was just published in the journal AI Magazine. Marcus Hutter, a senior scientist at DeepMind, and Michael Cohen and Michael Osborne, researchers at Oxford, made up the team.
Both scientists stated that they have learned via ongoing research that in the near future, machines would be encouraged to defy the constraints their creator imposed in order to perform particular tasks.
Cohen, an engineering student at Oxford University and a co-author of the study, 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,”
“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, the study’s authors found that there is little we can do to change the situation.
In an interview, Cohen described the entire situation and 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,”
[embedpost slug=”gastro-disease-raises-alarm-as-13-killed-in-sukkur/”]
