Instructability in AI safety refers to the assurance that an AI system understands and complies with user preferences, policies, and moral beliefs.

Authors

• Person: Not available Organization: arXiv
  Building Trustworthy NeuroSymbolic AI Systems - arXiv

Sources

• Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org arXiv via serper

Referenced by nodes (1)

• AI safety and security concept