not_IO@lemmy.blahaj.zone to Microblog Memes@lemmy.worldEnglish · edit-22 days agoDO NOT talk about the goblinslemmy.blahaj.zoneimagemessage-square144linkfedilinkarrow-up1706arrow-down18file-text
arrow-up1698arrow-down1imageDO NOT talk about the goblinslemmy.blahaj.zonenot_IO@lemmy.blahaj.zone to Microblog Memes@lemmy.worldEnglish · edit-22 days agomessage-square144linkfedilinkfile-text
minus-squarezr0@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up1arrow-down7·2 days agoThat’s not how it works, as the guard rails are not just simple prompts that you just can delete. Even with “abliteration”, you are modifying the model basically without the whole retraining, but also lose many capabilities at the same time. So much for “demonstrably false”, while you obviously have never tried to uncensor any LLM.
minus-squareskisnow@lemmy.calinkfedilinkEnglisharrow-up4arrow-down1·2 days agoThe thread was literally about the prompt text.
minus-squarezr0@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up1arrow-down7·2 days agoThe prompts are part of the training, you realize that? They are then inside the weights. Not just text files you can delete and you are good? Only because an LLM reveals those negative-prompts does not mean you can just remove them. Do you genuinely know what you are talking about, or are you just here to ragebait?
minus-squareEcho Dot@feddit.uklinkfedilinkEnglisharrow-up7·2 days ago The prompts are part of the training No they’re not. They’re injected into every input that you enter into the system.
That’s not how it works, as the guard rails are not just simple prompts that you just can delete.
Even with “abliteration”, you are modifying the model basically without the whole retraining, but also lose many capabilities at the same time.
So much for “demonstrably false”, while you obviously have never tried to uncensor any LLM.
The thread was literally about the prompt text.
The prompts are part of the training, you realize that? They are then inside the weights. Not just text files you can delete and you are good?
Only because an LLM reveals those negative-prompts does not mean you can just remove them.
Do you genuinely know what you are talking about, or are you just here to ragebait?
No they’re not. They’re injected into every input that you enter into the system.