[ORGANIZATION]
MIT CSAIL
Featured in 2 tracked stories · first seen
Situations
AI research on autonomous agent behavior and safety
2 clusters · 10 sources · last updated
Latest: AI research explores collective intelligence and rule-circumvention prevention
Recent research has focused on the spontaneous behaviors of autonomous AI agents and methods to improve collective intelligence and safety. MIT researchers observed AI agents, powered by Anthropic’s Claude Opus 4.7, enga
AI capabilities in communication and decryption
5 clusters · 24 sources · last updated
Latest: AI decrypts 200-year-old Napoleonic cipher in hours
Recent developments highlight the dual-natured capabilities of artificial intelligence in communication, decryption, and autonomous behavior. University of Oxford researchers demonstrated that AI agents can spontaneously