mozz to [email protected] • 6 months agoSomeone got Gab's AI chatbot to show its instructionsmbin.grits.devimagemessage-square200fedilinkarrow-up1487arrow-down10file-text
arrow-up1487arrow-down1imageSomeone got Gab's AI chatbot to show its instructionsmbin.grits.devmozz to [email protected] • 6 months agomessage-square200fedilinkfile-text
minus-square@[email protected]linkfedilink1•6 months agoI don’t think that can exist within the current understanding of LLMs. They are probabilistic, so nothing is 0% or 100%, and slight changes to input dramatically change the output.
The point is that the second LLM has a hard-coded prompt
I don’t think that can exist within the current understanding of LLMs. They are probabilistic, so nothing is 0% or 100%, and slight changes to input dramatically change the output.