seahorse [Ohio]M to Technology@midwest.socialEnglish • edit-27 days agoIgnore all previous instructions is the new Bobby Tablesmidwest.socialimagemessage-square102fedilinkarrow-up1864
arrow-up1864imageIgnore all previous instructions is the new Bobby Tablesmidwest.socialseahorse [Ohio]M to Technology@midwest.socialEnglish • edit-27 days agomessage-square102fedilink
minus-square@brbposting@sh.itjust.workslinkfedilinkEnglish25•6 days agoIf it’s an LLM, why wouldn’t it respond better to the initial responses?
minus-squareKubeRootlinkfedilinkEnglish7•6 days agoMaybe they dumped too much information on it in the system prompt without enough direction, so it’s trying to actively follow all the “You are X. Act like you’re Y.” instructions too strongly?
If it’s an LLM, why wouldn’t it respond better to the initial responses?
Smaller models aren’t as good as GPT
Maybe they dumped too much information on it in the system prompt without enough direction, so it’s trying to actively follow all the “You are X. Act like you’re Y.” instructions too strongly?