LughMA to FuturologyEnglish · 11 months agoSycophancy to subterfuge: Investigating reward tampering in language modelswww.anthropic.comexternal-linkmessage-square0linkfedilinkarrow-up18arrow-down10
arrow-up18arrow-down1external-linkSycophancy to subterfuge: Investigating reward tampering in language modelswww.anthropic.comLughMA to FuturologyEnglish · 11 months agomessage-square0linkfedilink