ono@lemmy.ca to Technology@beehaw.orgEnglish · 7 months agoLarge Language Models can Strategically Deceive their Users when Put Under Pressure [simulation led to insider trading]arxiv.orgexternal-linkmessage-square1fedilinkarrow-up125
arrow-up125external-linkLarge Language Models can Strategically Deceive their Users when Put Under Pressure [simulation led to insider trading]arxiv.orgono@lemmy.ca to Technology@beehaw.orgEnglish · 7 months agomessage-square1fedilink
minus-squareJustin@lemmy.jlh.namelinkfedilinkEnglisharrow-up6·7 months agoIt’s trained on human responses. Humans lie in their responses.