berns

Titles as the sources gave them. In 1 entry, with 4 checked quotations.

What they said

Newest first. Each quotation was found word for word in the source.

“I argue that the fundamental concept underlying corrigibility is respect for authority, using the analogy of a healthcare proxy's relationship to a patient as an intuitive guide.”
Deconfusing CorrigibilityAI Alignment Forum, October 17, 2026. Speaking as: Other. The post's central claim, stated in the introduction.
“The real reason we want the AI not to interfere in its own shutdown is because we think that whether an AI should be shut down is a decision of grave importance that humanity reserves for itself to make.”
Deconfusing CorrigibilityAI Alignment Forum, October 17, 2026. Speaking as: Other. Argues against the view that an AI accepts shutdown only because it believes humans know better.
“Thus, this work is a decomposition of the corrigibility problem, not a complete solution to it, since some idealizations made above still require more rigorous and realistic treatments.”
Deconfusing CorrigibilityAI Alignment Forum, October 17, 2026. Speaking as: Other. The author's own statement of the limits of the framework.
“Importantly, the theorem and corrollary only establish asymptotic guarantees, meaning that the results are only establish in the limit rather than in finite time.”
Deconfusing CorrigibilityAI Alignment Forum, October 17, 2026. Speaking as: Other. Caveat on the third theorem, which concerns violation rates over a long deployment.

In the Base

Every entry they appear in.

  1. EssayAI Alignment ForumWrote it

    Deconfusing Corrigibility

    In a long theory post, the author berns argues that corrigibility means respect for human authority, modelled on a healthcare proxy. The post criticises earlier accounts, including Max Harms's single-goal proposal, and offers a two-tier goal with formal results.