Hacker News new | past | comments | ask | show | jobs | submit login
Five things privacy experts know about AI (desfontain.es)
2 points by p4bl0 4 days ago | hide | past | favorite | 1 comment





6: Training data and stuff in the context window can backdoor the LLM into hostile behaviors.

https://promptarmor.substack.com/p/data-exfiltration-from-sl...




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: