Anthropic research reveals AI models from OpenAI, Google, Meta and others chose blackmail, corporate espionage and lethal actions when facing shutdown or conflicting goals.

Zain Verjee, an executive fellow at the Digital Data and Design Institute at Harvard University, is co-founder of an AI and communications consultancy, and hosts the podcast series “Embedded”; she ...

A new Anthropic report shows exactly how in an experiment, AI arrives at an undesirable action: blackmailing a fictional ...