Renneder@sh.itjust.worksM to BecomeMe@sh.itjust.works · 11 months agoSystematic testing of three Language Models reveals low language accuracy, absence of response stability, and a yes-response biaswww.pnas.orgexternal-linkmessage-square0fedilinkarrow-up19arrow-down11cross-posted to: [email protected]
arrow-up18arrow-down1external-linkSystematic testing of three Language Models reveals low language accuracy, absence of response stability, and a yes-response biaswww.pnas.orgRenneder@sh.itjust.worksM to BecomeMe@sh.itjust.works · 11 months agomessage-square0fedilinkcross-posted to: [email protected]