ono to Technology@beehaw.orgEnglish · 2 years agoLarge Language Models can Strategically Deceive their Users when Put Under Pressure [simulation led to insider trading]arxiv.orgexternal-linkmessage-square1linkfedilinkarrow-up127arrow-down10cross-posted to: [email protected][email protected]
arrow-up127arrow-down1external-linkLarge Language Models can Strategically Deceive their Users when Put Under Pressure [simulation led to insider trading]arxiv.orgono to Technology@beehaw.orgEnglish · 2 years agomessage-square1linkfedilinkcross-posted to: [email protected][email protected]
minus-squareJustin@lemmy.jlh.namelinkfedilinkEnglisharrow-up6·2 years agoIt’s trained on human responses. Humans lie in their responses.
