DevelopingOther
OpenAI Models Are Writing Their Own Jailbreak Instructions—And Sometimes Obeying Them
This event has not been summarised yet: the headline and the source list below come straight from the 1 report attached to it.
Affected entities
Original sources
| Publisher | Report | Role | Published |
|---|---|---|---|
| Decrypt Crypto media | OpenAI Models Are Writing Their Own Jailbreak Instructions—And Sometimes Obeying Them | Original |