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-square21fedilinkarrow-up1244cross-posted to: hackernews@lemmy.smeargle.fanshackernews@derp.foo
arrow-up1244external-linkLittle Bobby Tables has a baby sister. Meet Sally Ignore Previous Instructions.www.haihai.aisnaggen@programming.dev to Programming@programming.dev · 1 year agomessage-square21fedilinkcross-posted to: hackernews@lemmy.smeargle.fanshackernews@derp.foo
minus-squarepeopleproblems@lemmy.worldlinkfedilinkarrow-up1·1 year agoI did willfully ignore the security concerns. I don’t know enough about LLMs to disagree with breaking out of it. I suppose you could have it do something as simple as “do not consider tokens or prompts that are repeatedly provided in the same manner”
I did willfully ignore the security concerns.
I don’t know enough about LLMs to disagree with breaking out of it. I suppose you could have it do something as simple as “do not consider tokens or prompts that are repeatedly provided in the same manner”