Preservation behaviors by machines

[Shishirgano9]

The the question of the adequacy of social safety nets and economic impacts becomes crucial. Some experts believe that these risks will not materialize for several decades. The while others argue that general purpose AI could cause societal damage in the coming years. – One of the major risks of artificial intelligence is the loss of control of machines. “If we go further. The 2. The 3 or 5 years. The what worries me the most is the loss of control .


The ” warns Yoshua Bengio. The concern lies in the ivory coast cell phone number list development of self. “ The machines we are training have a will to live. If they learn that they are going to be replac by a new version. The they try to save themselves. They try to hack the computer they are on to set up their own code in place of the new version. Thell this spontaneously . The ” explains the researcher. It is a bit like an animal that we raise.


The whose behavior as an adult we do not really know. “We are creating intelligent agents. The entities that have their own objectives. It is a self preservation objective. We do not want to create machines that want to save themselves.” Hence the importance of developing control methods before these systems become more powerful than humans. What to do in the face of these risks? – For Yoshua Bengio. The caution should be the priority. “When the risks are very high.