| ▲ | brookst 2 hours ago | |||||||
Exactly. I don’t have the spare time but have been thinking that even a bit mask about provenance and policy could be prepended to the vector, then training could reinforce adherence, including having output tokens that indicate the provenance of the inputs used for the token. | ||||||||
| ▲ | crote 2 hours ago | parent [-] | |||||||
How does that guarantee anything? I could definitely see it being better, but that doesn't make violating it impossible does it? Just... statistically less likely. | ||||||||
| ||||||||