Gradient descent is what GPT-3 uses, I think, but humans wrote the equation by which the naive network gets its output(the next token prediction) ranked (for likeliness compared to the training data in this case). That’s it’s utility function right there, and that’s where we program in its (arbitrarily simple) goal. It’s not JUST a neural network. All ANN have another component.
Simple goals do not mean simple tasks.
I see what you mean that you can’t ‘force it’ to become general with a simple goal but I don’t think this is a problem.
For example: the simple goal of tricking humans out of as much of their money as possible is very simple indeed, but the task would pit the program against our collective general intelligence. A hill climbing optimization process could, with enough compute, start with inept ‘you won a prize’ popups and eventually create something with superhuman general intelligence with that goal.
It would have to be in perpetual training, rather then GPT-3′s train-then-use. Or was that GPT-2?
(Lots of people are trying to use computer programs for this right now so I don’t need to explain that many scumbags would try to create something like this!)
Gradient descent is what GPT-3 uses, I think, but humans wrote the equation by which the naive network gets its output(the next token prediction) ranked (for likeliness compared to the training data in this case). That’s it’s utility function right there, and that’s where we program in its (arbitrarily simple) goal. It’s not JUST a neural network. All ANN have another component.
Simple goals do not mean simple tasks.
I see what you mean that you can’t ‘force it’ to become general with a simple goal but I don’t think this is a problem.
For example: the simple goal of tricking humans out of as much of their money as possible is very simple indeed, but the task would pit the program against our collective general intelligence. A hill climbing optimization process could, with enough compute, start with inept ‘you won a prize’ popups and eventually create something with superhuman general intelligence with that goal.
It would have to be in perpetual training, rather then GPT-3′s train-then-use. Or was that GPT-2?
(Lots of people are trying to use computer programs for this right now so I don’t need to explain that many scumbags would try to create something like this!)