AI ethics and value alignment for nonhuman animals
S Ziesche - Philosophies, 2021 - mdpi.com
This article is about a specific, but so far neglected peril of AI, which is that AI systems may
become existential as well as causing suffering risks for nonhuman animals. The AI value …
become existential as well as causing suffering risks for nonhuman animals. The AI value …
Value cores for inner and outer alignment: simulating personality formation via iterated policy selection and preference learning with self-world modeling active …
Humanity faces multiple existential risks in the coming decades due to technological
advances in AI, and the possibility of unintended behaviors emerging from such systems …
advances in AI, and the possibility of unintended behaviors emerging from such systems …
NeuroAI for AI Safety
As AI systems become increasingly powerful, the need for safe AI has become more
pressing. Humans are an attractive model for AI safety: as the only known agents capable of …
pressing. Humans are an attractive model for AI safety: as the only known agents capable of …
[PDF][PDF] Dream of Being: Solving AI Alignment Problems with Active Inference Models of Agency and Socioemotional Value Learning
Humanity faces multiple existential risks in the coming decades due to technological
advances in AI, and the possibility of unintended behaviors emerging from such systems …
advances in AI, and the possibility of unintended behaviors emerging from such systems …
Value Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World Modeling Active …
J Hoey - Active Inference: Third International Workshop, IWAI …, 2023 - books.google.com
Humanity faces multiple existential risks in the coming decades due to technological
advances in AI, and the possibility of unintended behaviors emerging from such systems …
advances in AI, and the possibility of unintended behaviors emerging from such systems …
[PDF][PDF] Value Coalition Cores for Inner and Outer Alignment: Simulating Personality Formation via Iterated Policy Selection and Preference Learning with Self-World …
A Safron11, Z Sheikhbahaee21, N Hay, J Orchard… - researchgate.net
Humanity faces multiple existential risks in the coming decades due to technological
advances in AI, and the possibility of unintended behaviors emerging from such systems …
advances in AI, and the possibility of unintended behaviors emerging from such systems …
[PDF][PDF] Dream of Being: An Active Inference Approach to Agency and Value Recognition in Socioemotional Contexts for Handling AI Alignment Problems
A Safron11, Z Sheikhbahaee21, N Hay, J Orchard… - researchgate.net
Humanity faces multiple existential risks in the coming decades due to technological
advances in AI, and the possibility of unintended behaviors emerging from such systems …
advances in AI, and the possibility of unintended behaviors emerging from such systems …