Pith. sign in

The Alignment Problem: Machine Learning and Human Values

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Machine Theory of Mind and the Structure of Human Values

cs.AI · 2025-05-24 · conditional · novelty 5.0

Human values are claimed to have a rational instrumental structure that lets AI infer unseen values from known ones, framing this as the 'value generalization problem' in AI safety.

citing papers explorer

Showing 1 of 1 citing paper.

  • Machine Theory of Mind and the Structure of Human Values cs.AI · 2025-05-24 · conditional · none · ref 6

    Human values are claimed to have a rational instrumental structure that lets AI infer unseen values from known ones, framing this as the 'value generalization problem' in AI safety.