Micah Carroll
@MicahCarroll
I'm all for looking for alternatives to CoT for maintaining monitorability, but are they going to be ready in a couple of months?
CoT is fragile and limited as no-CoT time-horizons increase, but it'll be the best tool we'll have by default until proven otherwise
CoT is fragile and limited as no-CoT time-horizons increase, but it'll be the best tool we'll have by default until proven otherwise
Leo Gao@nabla_theta · Sep 2imo not having good CoT makes life harder: you need more mechinterp just to get to the same level of monitorability.
i also think it's unlikely mechinterp will be that good in a year. the current state is either pragmatic stuff (NLAs, oracles) all have to depend on rickety magic
Open quoted post →i also think it's unlikely mechinterp will be that good in a year. the current state is either pragmatic stuff (NLAs, oracles) all have to depend on rickety magic
· Edited
7 101