Reasoning about causality in games (abstract reprint)

[Free GPT-4]
[PDF] arxiv.org

NeuroAI for AI Safety

P Mineault, N Zanichelli, JZ Peng, A Arkhipov… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …
Salva Cita Articoli correlati Tutte e 2 le versioni Versione HTML