That seems like quite a leap. If there is one particular development in humanity’s history that we can fully explain, we should then not cite evolution in any way, as an argument for anything?
is not implied by what Quintin actually said. Perhaps you’re making an error in interpretation? See the next paragraph where you say “directly apply”:
If we applied this standard to other forms of reference class arguments, then presumably we would throw most or almost all of them out as well—anything where the particular mechanism was understood, and didn’t directly apply to AI, would not count. I do not see Quintin or other skeptics proposing this standard of evidence more generally, nor do I think it would make sense.
Quintin is just saying there has to be some analogy between something to do with AI development and a phenomena in a putative reference class. Which is obvious, because reference class forecasting is when you take some group of things which have tight analogies between each other. All you’re doing is claiming “this thing has a tight analogy with elements of this class” and using the analogy to predict things. Whether the analogy is “direct” is irrelevant.
As an example showing Quintin’s claim is reasonable, let’s consider a diferent case: evolution vs voting. Evolution selects over individuals, and doesn’t select over groups in general. If some odd circumstances obtain, then it can effectively select over groups. But that’s not true by default. We understand this through things like the class of theorems which generalize Fisher’s (poorly named) fundamental theorem of natural selection, whose assumptions fit empirical observations.
Now, if you said “evolution is an optimization procedure, it doesn’t select for groups by default because of this mechanism right here (Fisher’s …). There is nothing analagous to this mechanism in this other optimization procedure e.g. first past the post voting for political candidates and parties, where the mechanism has groups of people built into it. No analogy showing group selection need not occur can be made, even an indirect one, without risking a contradiction. ” is totally sensible.
This statement:
is not implied by what Quintin actually said. Perhaps you’re making an error in interpretation? See the next paragraph where you say “directly apply”:
Quintin is just saying there has to be some analogy between something to do with AI development and a phenomena in a putative reference class. Which is obvious, because reference class forecasting is when you take some group of things which have tight analogies between each other. All you’re doing is claiming “this thing has a tight analogy with elements of this class” and using the analogy to predict things. Whether the analogy is “direct” is irrelevant.
As an example showing Quintin’s claim is reasonable, let’s consider a diferent case: evolution vs voting. Evolution selects over individuals, and doesn’t select over groups in general. If some odd circumstances obtain, then it can effectively select over groups. But that’s not true by default. We understand this through things like the class of theorems which generalize Fisher’s (poorly named) fundamental theorem of natural selection, whose assumptions fit empirical observations.
Now, if you said “evolution is an optimization procedure, it doesn’t select for groups by default because of this mechanism right here (Fisher’s …). There is nothing analagous to this mechanism in this other optimization procedure e.g. first past the post voting for political candidates and parties, where the mechanism has groups of people built into it. No analogy showing group selection need not occur can be made, even an indirect one, without risking a contradiction. ” is totally sensible.