causal claim
The speaker says the model's initialization data produced depressed behavior even after examples of depressed models were removed from the data.
Ryan Greenblatt · Ryan Greenblatt – What happens once AI can automate AI research? · 11 Aug 2026
In their words
The transcript segments this claim was taken from
“but the initialization data for their model made it depressed even after filtering out all of the examples of models being depressed from that data. So they like take a base model,”Play from 2:05:54Report a misattribution
90%how strongly it was put, not whether it is true
85%importance to the conversation
94%confidence the claim was read correctly