Designing a Safe Autonomous Artificial Intelligence Agent based on Human Self-Regulation

📖 Description

Designing a Safe Autonomous Artificial Intelligence Agent based on Human Self -Regulation Mark Muraven University at Albany January 5, 2017 Author contact: [email removed] Human Self -Regulation for AI 2 Abstract There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanism s may cause AI agents to engage in unwanted and harmful outcomes. Thus it is necessary to design AI agents that follow initial programming intentions as the program grows in complexity. How to specify these initial intentions has also been an obstacle to designing safe AI agents. Finally, there is a need for the AI agent to have redundant safety mechanisms to ensure that any programming errors do not cascade into major problems. Humans are autonomous intelligent agents that have avoided these problems and t he present manuscript argues that by understanding human self -regulation and go...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1701.01487