Buck Shlegeris
@bshlgrs
CEO@Redwood Research (@redwood_ai), working on technical research to reduce catastrophic risk from AI misalignment. bshlegeris@gmail.com
가입 January 2015
364 팔로잉 중 6.3K 팬
I've been concerned about CoT monitorability breaking down for years. This could happen for several reasons, but architectural changes that increase opaque serial depth are a particularly likely route to massively degraded monitorability.
더 보기
Some architectures could weaken CoT monitorability, or remove the CoT altogether.
We've written a proposal for how companies could be transparent about no-CoT reasoning abilities, other monitorability evidence, and policies for preserving monitorability.
더 보기
