> it's interesting to play around with a local model where you can edit the output and then have the model continue it.
It's so interesting that there is a whole set of prompt injection attacks called prefilling attacks that attempt to do a thing similar to that - load the LLM context in a way to make it predict tokens as if the LLM (instead of the System or the User) wrote something to get it to change it's behavior.
It's so interesting that there is a whole set of prompt injection attacks called prefilling attacks that attempt to do a thing similar to that - load the LLM context in a way to make it predict tokens as if the LLM (instead of the System or the User) wrote something to get it to change it's behavior.