I think that designing useful models that are resilient to prompt injection is substantially harder than training a model to self-identify as a human. For instance, you may still be able to inject such a model with…
Very interesting. I was trying to play around with it, but could not find the known concept IDs to steer the model, are they yet to be released?
I think that designing useful models that are resilient to prompt injection is substantially harder than training a model to self-identify as a human. For instance, you may still be able to inject such a model with…
Very interesting. I was trying to play around with it, but could not find the known concept IDs to steer the model, are they yet to be released?