RandAlThor@lemmy.ca to World News@lemmy.worldEnglish · 2 days agoElon Musk’s Grok Says It Would Kill Every Jewish Person on the Planet to Save Himwww.mediaite.comexternal-linkmessage-square89fedilinkarrow-up1507arrow-down120cross-posted to: [email protected]
arrow-up1487arrow-down1external-linkElon Musk’s Grok Says It Would Kill Every Jewish Person on the Planet to Save Himwww.mediaite.comRandAlThor@lemmy.ca to World News@lemmy.worldEnglish · 2 days agomessage-square89fedilinkcross-posted to: [email protected]
minus-squareCredibly_Human@lemmy.worldlinkfedilinkEnglisharrow-up1·4 hours agoBecause a lot of the safe gaurds work by simply pre prompting the next token guesser to not guess things they don’t want it to do. Its in plain english using the “logic” of conversations, so the same vulnerabilities largely apply to those methods.
Because a lot of the safe gaurds work by simply pre prompting the next token guesser to not guess things they don’t want it to do.
Its in plain english using the “logic” of conversations, so the same vulnerabilities largely apply to those methods.