Christiano, 2018 — Supervising Strong Learners by Amplifying Weak Experts

DOI: <a href="https://doi.org/10.48550/arXiv.1810.08575" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.1810.08575
URL: <a href="https://arxiv.org/abs/1810.08575" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/1810.08575

Presents a scalable oversight proposal or failure mode for supervising systems stronger than their overseers.

Publication links

Presents a scalable oversight proposal or failure mode for supervising systems stronger than their overseers.