build1 distinct publisher
Your model cannot tell your instructions from the customer's, and that is the whole bug
A dev.to post argues prompt hardening is the weakest defence against injection, not the strongest. If your security depends on the model choosing to obey, you have a suggestion.
Publishers:dev.to
Reality
- Evidence34
- Adoption
- Insufficient
- Hype gap+12
- Incentives
- Insufficient
- Confidence38