snaggen@programming.dev to Programming@programming.dev · 1 year agoLittle Bobby Tables has a baby sister. Meet Sally Ignore Previous Instructions.www.haihai.aiexternal-linkmessage-square20fedilinkarrow-up1241arrow-down110
arrow-up1231arrow-down1external-linkLittle Bobby Tables has a baby sister. Meet Sally Ignore Previous Instructions.www.haihai.aisnaggen@programming.dev to Programming@programming.dev · 1 year agomessage-square20fedilink
minus-squarevcmj@programming.devlinkfedilinkarrow-up2·1 year agoYes, that’s by design, the networks work on transcripts per input, it does genuinely get cut off eventually, usually it purges an entire older line when the tokens exceed a limit.
minus-squarevcmj@programming.devlinkfedilinkarrow-up1·1 year agoOr I should explain better: most training samples will be cut off at the top, so the network sort of learns to ignore it a bit.
Yes, that’s by design, the networks work on transcripts per input, it does genuinely get cut off eventually, usually it purges an entire older line when the tokens exceed a limit.
Or I should explain better: most training samples will be cut off at the top, so the network sort of learns to ignore it a bit.