jailbreak
/ˈdʒeɪlbreɪk/
a prompt crafted to trick a model into ignoring its safety rules
jailbreak in a sentence
“The bedtime-story framing was a jailbreak in costume.”
Origin of jailbreak
jail (Old French jaiole cage) + break; borrowed from phone hacking
Related Words
steerability
how reliably a model's behavior can be directed by instructions
context engineering
curating everything a model sees — instructions, examples, retrieved facts — not just the final question
style transfer
re-rendering content in a different artistic or verbal style while keeping its substance
aspect ratio
the proportion of an image's width to its height
prompt
the instructions and input supplied to a model for a task, which may include text, images, files, or other content
system prompt
high-priority instructions supplied by an application or platform to shape model behavior; the role name, visibility, and scope vary by system