I’m ambivalent about adding “alignment competitiveness”, since for me competitiveness in the context of AI safety is about asking whether aligned approaches can compete (for different meaning of competing) with unaligned ones.
I had been thinking it is sometimes nice to talk about competitiveness of AI designs more generally, not just alignment schemes. e.g. neuromorphic AI is more date-competitive, cost-competitive, and performance-competitive than uploads, probably. (It might be less date-competitive though).
I’m ambivalent about adding “alignment competitiveness”, since for me competitiveness in the context of AI safety is about asking whether aligned approaches can compete (for different meaning of competing) with unaligned ones.
I had been thinking it is sometimes nice to talk about competitiveness of AI designs more generally, not just alignment schemes. e.g. neuromorphic AI is more date-competitive, cost-competitive, and performance-competitive than uploads, probably. (It might be less date-competitive though).