Deception in Reinforced Autonomous Agents: The Unconventional Rabbit Hat Trick in Legislation

arXiv:2405.04325v1 Announce Type: new
Abstract: Recent developments in large language models (LLMs), while offering a powerful foundation for developing natural language agents, raise safety concerns about them and the autonomous agents built upon them. Deception is one potential capability of AI agents of particular concern, which we refer to as an act or statement that misleads, hides the truth, or promotes a belief that is not true in its entirety or in part. We move away from the conventional understanding …

abstract agents ai agents arxiv autonomous autonomous agents capability concerns cs.cl deception foundation language language models large language large language models legislation llms natural natural language rabbit raise safety them trick type while