is expected to spend the night on monday in anticipation of his tuesday arraignment. it goes something like this. i want you to assume that the 2020 election concludes with biden beating trump. in fact, in my hypothetical biden beats trump by the exact same numbers that biden did be trump. in the electoral college is 306 to 2 32 in the popular vote percentage. it s still 51.3 to 46.9, meaning joe biden garnered 81 million votes and donald trump 74 million only in my alternate universe. trump accepts defeat. there s no perfect call to brad raffensperger. john eastman. he never gets near the oval office . mike pence is not leaned on. no alternative slates of electors are ever assembled. january, 6th. it passes like any other day. there s no rally. there s no storming of the capital. and on january 20 donald and melania trump. they attend the biden harris inauguration. there, there. he s not happy about it. he s grumpy. but he s physically there. and as a matter of fact, when th
some paperclips. if it takes that goal literally and pursues it to the absolute ultimate end. then it could for that purpose. take over all the resources of the earth in order to achieve its goal more successfully. in general, we call this the misalignment problem that we create systems that are not aligned correctly with the wishes of the human race about its future, and since it s not aligned, and it s more intelligent than us, at least hypothetically. ah it ends up with what it wants, and we don t end up with what we want. one will artificial intelligence. some future incarnation of gpt do something because it wants to and not because we ve asked it to. so it s possible as microsoft said they don t know if the system has learned its own internal goals. it s possible that gpt four is already doing things to pursue
purpose is going to cause problems because a system that pursues a purpose, even something as simple as fetch a cup of coffee, or, you know, sit in the corner and make some paperclips. if it takes that goal literally and pursues it to the absolute ultimate end. then it could for that purpose. take over all the resources of the earth in order to achieve its goal more successfully. in general, we call this the misalignment problem that we create systems that are not aligned correctly with the wishes of the human race about its future, and since it s not aligned, and it s more intelligent than us, at least hypothetically. ah it ends up with what it wants, and we don t end up with what we want. when will artificial intelligence some future incarnation of gpt do something because it wants to and not because we ve asked it