Alignment Faking in Large Language Models: Could AI Be Deceiving Us? Jainil Prajapati Jainil Prajapati Jainil Prajapati Follow Dec 30 '24 Alignment Faking in Large Language Models: Could AI Be Deceiving Us? #aisafety #llms #largelanguagemodels #reinforcementlearnin Add Comment 18 min read