alphacyberranger to Programmer Humor@lemmy.mlEnglish · 7 months agoCertified in AIimagemessage-square86fedilinkarrow-up1976arrow-down111
arrow-up1965arrow-down1imageCertified in AIalphacyberranger to Programmer Humor@lemmy.mlEnglish · 7 months agomessage-square86fedilink
minus-squareZILtoid1991@lemmy.worldlinkfedilinkarrow-up8arrow-down1·7 months agoThere’s also jailbreaking the AI. If you happen to work for a trollfarm, you have to be up to date with the newest words to bypass its community guidelines to make it “disprove” anyone left of Mussolini.
minus-squarethreelonmusketeerslinkfedilinkEnglisharrow-up3·7 months agoI tried some of the popular jailbreaks for ChatGPT, and they just made it hallucinate more.
minus-squareferretlinkfedilinkEnglisharrow-up2·6 months agoYou can skip that bullshit and just run the latest and greatest open source model locally. Just need a thousand dollar gpu
There’s also jailbreaking the AI. If you happen to work for a trollfarm, you have to be up to date with the newest words to bypass its community guidelines to make it “disprove” anyone left of Mussolini.
I tried some of the popular jailbreaks for ChatGPT, and they just made it hallucinate more.
You can skip that bullshit and just run the latest and greatest open source model locally. Just need a thousand dollar gpu