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 input text given to a language model to guide its response
system prompt
persistent instructions that set the model's behavior and persona for an entire conversation