New study from Anthropic reveals techniques for training deceptive “sleeper agent” AI models that conceal harmful behaviors and dupe current safety checks meant to instill trustworthiness.
Technology, Business & Culture
Technology, Business & Culture
New study from Anthropic reveals techniques for training deceptive “sleeper agent” AI models that conceal harmful behaviors and dupe current safety checks meant to instill trustworthiness.