Savlar4 sources healthy · latest episode 20 Oct 2026
opinion claim

The speaker's defense of AI systems in many cases is that they were not trained on the task being evaluated.

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

“One other thing I was going to mention, which is a new topic sort of, is that I think in a lot of these cases, my defense of the AI is that,”
“well, they never were trained on this task.”
Play from 1:14:44Report a misattribution
85%how strongly it was put, not whether it is true
65%importance to the conversation
90%confidence the claim was read correctly