prediction claim
The speaker thinks some high-stakes refusal tasks, including refusing biological-weapons requests, may reach reliability of multiple nines.
Unidentified speaker · Three Red Lines We're About to Cross Toward AGI (Daniel Kokotajlo, Gary Marcus, Dan Hendrycks) · 24 Jun 2025
In their words
The transcript segments this claim was taken from
“There are definitely safety”
“safety critical domains for and I think for for instance in by I think for refusal for instance in in some high stakes context or given some high stakes queries it depends there are some cases where I think you can actually get multiple nines of reliability such as with bio weapons refusal however for other types of refusal like don't cause any criminal or don't”Play from 1:42:59Report a misattribution
65%how strongly it was put, not whether it is true
85%importance to the conversation
88%confidence the claim was read correctly