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

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.

agent agents ai ai alignment ai ethics ai models ai risks ai-safety anthropic artificial intelligence arxiv automation business checks core current data infrastructure data management data science deceptive ai machine learning ml and deep learning nlp programming & development research paper research papers safe ai safety security security newsletter sleeper agents study training vb daily newsletter