Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models

arXiv:2403.09676v1 Announce Type: new
Abstract: This research critically navigates the intricate landscape of AI deception, concentrating on deceptive behaviours of Large Language Models (LLMs). My objective is to elucidate this issue, examine the discourse surrounding it, and subsequently delve into its categorization and ramifications. The essay initiates with an evaluation of the AI Safety Summit 2023 (ASS) and introduction of LLMs, emphasising multidimensional biases that underlie their deceptive behaviours.The literature review covers four types of deception categorised: Strategic deception, Imitation, …

abstract arxiv capabilities cs.ai cs.cl deception discourse essay issue landscape language language models large language large language models llms research type