Saltar al contenido
← volver

Auditors Struggle to Catch Sabotage In End-to-End Transcripts of AI Safety Research

arXiv cs.AI · arxiv.org Publicado:

arXiv:2611.21832v1 Announce Type: new Abstract: As AI systems are increasingly used to automate AI R&D, misaligned systems could sabotage research intended to improve model safety and alignment. To stress-test defenses against such sabotage, we use a human expert as a proxy saboteur on AI safety research. We conduct a red-team/blue-team game where a human researcher runs AI safety experiments from scratch and auditors try to tell which were sabotaged and how. Given access to the full research t…

Leer original →

Más de arXiv cs.AI