Do you expect these results to hold in more complex environments? My main concern with APPS is always that the attack surface is unrealistically constrained.
Maybe you intended to post this as a comment on this post on APPS backdoors? I agree for APPS backdoors it seems like an important limitation.
But in this post I explore math problems, where I want to find things that don’t look like math reasoning that helps with answering math questions, which seems complex and should in principle have a large attack surface.
Do you expect these results to hold in more complex environments? My main concern with APPS is always that the attack surface is unrealistically constrained.
Maybe you intended to post this as a comment on this post on APPS backdoors? I agree for APPS backdoors it seems like an important limitation.
But in this post I explore math problems, where I want to find things that don’t look like math reasoning that helps with answering math questions, which seems complex and should in principle have a large attack surface.
Ah your right! Sorry about that