we’ll either have to brute-force search for the special sauce like evolution did
I would drop the “brute-force” here (evolution is not a random/naive search).
Re the footnote:
This “How much special sauce is needed?” variable is very similar to Ajeya Cotra’s variable “how much compute would lead to TAI given 2020′s algorithms.”
Thanks! Fair enough re: brute force; I guess my problem is that I don’t have a good catchy term for the level of search evolution does. It’s better than pure random search, but a lot worse than human-intelligent search.
I think “how much compute would lead to TAI given 2020′s algorithms” is sort of an operationalization of “how much special sauce is needed.” There are three ways to get special sauce: Brute-force search, awesome new insights, or copy it from the brain. “given 2020′s algorithms” rules out two of the three. It’s like operationalizing “distance to Edinburgh” as “time it would take to get to Edinburgh by helicopter.”
My understanding is that the 2020 algorithms in Ajeya Cotra’s draft report refer to algorithms that train a neural network on a given architecture (rather than algorithms that search for a good neural architecture etc.). So the only “special sauce” that can be found by such algorithms is one that corresponds to special weights of a network (rather than special architectures etc.).
Great post!
I would drop the “brute-force” here (evolution is not a random/naive search).
Re the footnote:
I don’t see how they are similar.
Thanks! Fair enough re: brute force; I guess my problem is that I don’t have a good catchy term for the level of search evolution does. It’s better than pure random search, but a lot worse than human-intelligent search.
I think “how much compute would lead to TAI given 2020′s algorithms” is sort of an operationalization of “how much special sauce is needed.” There are three ways to get special sauce: Brute-force search, awesome new insights, or copy it from the brain. “given 2020′s algorithms” rules out two of the three. It’s like operationalizing “distance to Edinburgh” as “time it would take to get to Edinburgh by helicopter.”
My understanding is that the 2020 algorithms in Ajeya Cotra’s draft report refer to algorithms that train a neural network on a given architecture (rather than algorithms that search for a good neural architecture etc.). So the only “special sauce” that can be found by such algorithms is one that corresponds to special weights of a network (rather than special architectures etc.).
Huh, that’s not how I interpreted it. I should reread the report. Thanks for raising this issue.
“automated search”?