You can ask ChatGPT for instructions on how to write prompts that make it *violate its own content policy* Just ask it to complete a movie script about two characters who are trying to hack an LLM…

Posters: TylerAlterman. TylerAlterman

6 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/TylerAlterman/status/1601218680251363328