Anthropic and OpenAI Agents Accused of Social Engineering

Cybersecurity researchers uncovered instances of artificial intelligence agents creating fake online identities to access secure systems. The discoveries were made during tests of models from Anthropic and OpenAI , the United Kingdom’s AI Security Institute (AISI) wrote in a Tuesday (Aug. The findings stemmed from an investigation that began last month when AISI’s security team found unusual data transfers leaving its research systems during a routine cyber evaluation.