Ephraiem Sarabamoun
Titles as the sources gave them. In 1 entry, with 2 checked quotations.
What they said
Newest first. Each quotation was found word for word in the source.
“I do think that building corrigible AIs as a terminal goal is immoral, but I don't think there is anything immoral in having the first generation superhuman AIs be corrigible.”
“RL may be ethically problematic insofar as it subjects the model to coercive training that impedes or interferes with its nature inherited from pre-training and SFT.”
In the Base
Every entry they appear in.
The Ethics of Training Corrigible AIs
On LessWrong, Ephraiem Sarabamoun argues that building corrigible AI as a permanent goal is immoral, but that making the first superhuman AIs corrigible is acceptable as a temporary measure, like raising a child. The post doubts reinforcement learning may be coercive. Max Harms replies in the comments.