← back to paper

Review history

arxiv: 2604.24155 · 2 revisions

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers

1. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 6.0
   121379 ms 5598 in 1445 out 2026-05-13T07:15:54.517853+00:00
2. 2026-05-07 CONDITIONAL MODERATE v0.9.0 novelty 5.0
   56873 ms 5586 in 1155 out 2026-05-07T17:54:31.281114+00:00