Garrabrant, 2017 — Logical induction

DOI: <a href="https://doi.org/10.48550/arXiv.1609.03543" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.1609.03543
URL: <a href="https://arxiv.org/abs/1609.03543" target="_blank" rel="noopener noreferrer">https://arxiv.org/abs/1609.03543

AI alignment or ML-safety source grounding the agent, oversight, or capability argument. Focus: Logical induction.

Publication links

AI alignment or ML-safety source grounding the agent, oversight, or capability argument. Focus: Logical induction.