It feels like there is an implicit assumption in CFAR’s agenda that most of the important things are going to happen in one or two decades from now.
I don’t think this; it seems to me that the next decade or two may be pivotal, but they may well not be, and the rest of the century matters quite a bit as well in expectation.
There are three main reasons we’ve focused mainly on adults:
Adults can contribute more rapidly, and so can be part of a process of compounding careful-thinking resources in a shorter-term way. E.g. if adults are hired now by MIRI, they improve the ratio of thoughtfulness within those thinking about AI safety, and this can in turn impact the culture of the field, the quality of future years’ research, etc.
For reasons resembling (1), adults provide a faster “grounded feedback cycle”. E.g., adults who come in with business or scientific experience can tell us right away whether the curricula feel promising to them; students and teens are more likely to be indiscriminatingly enthusiastic. .
Adults can often pay their own way at the workshops; children can’t; we therefore cannot afford to run very many workshops for kids until we somehow acquire either more donation, or more financial resource in some other way.
Nevertheless, I agree with you that programs targeting children can be higher impact per person and are extremely worthwhile in the medium- to long-run. This is indeed part of the motivation for SPARC, and expanding such programs is key to our long-term aims; marginal donation is key to our ability to do these quickly, and not just eventually.
I don’t think this; it seems to me that the next decade or two may be pivotal, but they may well not be, and the rest of the century matters quite a bit as well in expectation.
There are three main reasons we’ve focused mainly on adults:
Adults can contribute more rapidly, and so can be part of a process of compounding careful-thinking resources in a shorter-term way. E.g. if adults are hired now by MIRI, they improve the ratio of thoughtfulness within those thinking about AI safety, and this can in turn impact the culture of the field, the quality of future years’ research, etc.
For reasons resembling (1), adults provide a faster “grounded feedback cycle”. E.g., adults who come in with business or scientific experience can tell us right away whether the curricula feel promising to them; students and teens are more likely to be indiscriminatingly enthusiastic. .
Adults can often pay their own way at the workshops; children can’t; we therefore cannot afford to run very many workshops for kids until we somehow acquire either more donation, or more financial resource in some other way.
Nevertheless, I agree with you that programs targeting children can be higher impact per person and are extremely worthwhile in the medium- to long-run. This is indeed part of the motivation for SPARC, and expanding such programs is key to our long-term aims; marginal donation is key to our ability to do these quickly, and not just eventually.