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.”2:06:15Report a misattribution
0.90how strongly it was put, not whether it is true
0.80importance to the conversation
0.96confidence the claim was read correctly