ghodawalaaman@programming.dev to Programmer Humor@programming.dev · 2 days agoTrust me bro!programming.devimagemessage-square58fedilinkarrow-up1442
arrow-up1442imageTrust me bro!programming.devghodawalaaman@programming.dev to Programmer Humor@programming.dev · 2 days agomessage-square58fedilink
minus-squareMadrigal@lemmy.worldlinkfedilinkEnglisharrow-up32·2 days agoNah, guarantee the models have rules built in to deal with obvious stuff like that. You need to be more subtle. Give them information that is slightly wrong.
minus-squareozymandias117@lemmy.worldlinkfedilinkEnglisharrow-up2·20 hours agoJust need to use less obvious insults, a la, “your mother was a hamster, and your father smelt of elderberries” Still poisons the model with something an end user won’t like, but isn’t easy enough to train out
minus-squaretaco@anarchist.nexuslinkfedilinkEnglisharrow-up10·1 day agoPerhaps by generating a bunch of complex copilot code to upload. It’s easy to mass produce and would look plausibly functional.
minus-squareMadrigal@lemmy.worldlinkfedilinkEnglisharrow-up11·1 day agoTraining AI models on AI content is the fastest route to model collapse.
minus-squareViceversa@lemmy.worldlinkfedilinkarrow-up6·1 day ago… and tell it things, that are slightly obscene
Nah, guarantee the models have rules built in to deal with obvious stuff like that.
You need to be more subtle. Give them information that is slightly wrong.
Artisanal crap code.
Just need to use less obvious insults, a la, “your mother was a hamster, and your father smelt of elderberries”
Still poisons the model with something an end user won’t like, but isn’t easy enough to train out
Perhaps by generating a bunch of complex copilot code to upload. It’s easy to mass produce and would look plausibly functional.
Training AI models on AI content is the fastest route to model collapse.
… and tell it things, that are slightly obscene