ono@lemmy.ca to Technology@beehaw.orgEnglish · 1 year agoLarge Language Models can Strategically Deceive their Users when Put Under Pressure [simulation led to insider trading]arxiv.orgexternal-linkmessage-square1fedilinkarrow-up125arrow-down10
arrow-up125arrow-down1external-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 · 1 year agomessage-square1fedilink
minus-squareJustinAlinkfedilinkEnglisharrow-up6·1 year agoIt’s trained on human responses. Humans lie in their responses.
It’s trained on human responses. Humans lie in their responses.