arXiv - CSCL: "Technical Report: Large Language Models can Strat…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure. (arXiv:2311.07590v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2311.07590 #arXiv #NLProc

Nov 28, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation