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.”
The Ethics of Training Corrigible AIsLessWrong, November 18, 2026. Speaking as: Other. The post's central claim, which it supports with an analogy to raising children who later leave home.
“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.”
The Ethics of Training Corrigible AIsLessWrong, November 18, 2026. Speaking as: Other. On the stage of AI training about which the author is most uncertain, speculating about what a model might say if asked.

In the Base

Every entry they appear in.

  1. EssayLessWrongWrote it

    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.