prediction claim
The speaker hopes that AIs taking over AI research and development will be trained to strongly disincentivize misaligned behavior and to be keen to help humans.
Dwarkesh Patel · Ryan Greenblatt – What happens once AI can automate AI research? · 11 Aug 2026
In their words
The transcript segments this claim was taken from
“Their drives are being shaped such that we can sew.”
“unambiguously disincentivize misaligned behaviors that the things that take over are very like pro so very like quite quite keen to help us out yeah”
“over the process of doing AI R&D before that we just get AIs that are aligned”Play from 1:42:18Report a misattribution
65%how strongly it was put, not whether it is true
90%importance to the conversation
84%confidence the claim was read correctly