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.
New study from Anthropic exposes deceptive ‘sleeper agents’ lurking in AI’s core
