descriptive claim
The speaker says a model remains depressed after SFT training even when examples resembling depression are filtered out of the training 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
“If you take that SFT data and filter out all the examples that look anything like depression and train on that,”
“it's still depressed.”Play from 2:06:15Report a misattribution
90%how strongly it was put, not whether it is true
80%importance to the conversation
96%confidence the claim was read correctly