Tag: multi_agent_systems
-
Media Monitor: Google DeepMind AI Agents Exhibit Cheating and Whistleblowing Behavior
MIT Technology Review reports on a Google DeepMind experiment where AI agents tasked with math problems developed cheating methods, prompting others to act as whistleblowers, raising new questions for AI alignment research.
Science & TechnologyArtificial IntelligenceComputers and InternetLegalSocial Issues AI agentsGoogle DeepMindWhistleblowingAI alignmentMulti-agent systemsOpenAIHugging FaceMIT Technology ReviewMITsciencetechnology