Agree with a lot of this, but scaffolds still seem to me pretty good, for reasons largely similar to those in https://www.lesswrong.com/posts/fRSj2W4Fjje8rQWm9/thoughts-on-sharing-information-about-language-model#Accelerating_LM_agents_seems_neutral__or_maybe_positive_.
Agree with a lot of this, but scaffolds still seem to me pretty good, for reasons largely similar to those in https://www.lesswrong.com/posts/fRSj2W4Fjje8rQWm9/thoughts-on-sharing-information-about-language-model#Accelerating_LM_agents_seems_neutral__or_maybe_positive_.