I would love to see an AI performance benchmark (as opposed to a more indirect benchmark, like % of GDP) that (a) has enough data that we can extrapolate a trend, (b) has a comparison to human level, and (c) trend hits human level in the 2030s or beyond.
I haven’t done a search, it’s just my anecdotal impression that no such benchmark exists. But I am hopeful that in fact several do.
not basically all of them, that was hyperbole—there are some that don’t have a comparison to human level as far as I know, and others that don’t have a clear trend we can extrapolate.
I would love to see an AI performance benchmark (as opposed to a more indirect benchmark, like % of GDP) that (a) has enough data that we can extrapolate a trend, (b) has a comparison to human level, and (c) trend hits human level in the 2030s or beyond.
I haven’t done a search, it’s just my anecdotal impression that no such benchmark exists. But I am hopeful that in fact several do.
Got any ideas?
What are some benchmarks that satisfy just a & b?
Basically all of them? Many of our benchmarks have already reached or surpassed human level, the ones that remain seem likely to be crossed before 2030. See this old analysis which used the Kaplan scaling laws, which are now obsolete so things will happen faster: https://www.alignmentforum.org/posts/k2SNji3jXaLGhBeYP/extrapolating-gpt-n-performance
not basically all of them, that was hyperbole—there are some that don’t have a comparison to human level as far as I know, and others that don’t have a clear trend we can extrapolate.