Hubinger, 2019 — Risks from Learned Optimization in Advanced Machine Learning Systems

DOI: <a href="https://doi.org/10.48550/arXiv.1906.01820" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.1906.01820
URL: <a href="https://arxiv.org/abs/1906.01820" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/1906.01820

Highlights a concrete AI-risk mechanism involving deception, inner optimization, control failure, or capability jumps.

Publication links

Highlights a concrete AI-risk mechanism involving deception, inner optimization, control failure, or capability jumps.