definition
Jailbreaks Coax or Confuse Models Into Forbidden Output
Jailbreaking an LLM means coaxing it to produce things it was trained not to say, either through human-readable pretense (e.g., 'pretend you're not saying it') or through nonsensical symbol sequences meaningless to humans that nonetheless trigger unexpected, unsafe model behavior, representing a safety concern.
definitionpending
Speaker
Yejin ChoiEvidence Quote
“one version is trying to coax basically ChatGPT to say things that it's trained not to say potentially toxic stuff or how to commit crime”
Created: 6/13/2026, 12:23:11 AM
Your notes
Loading notes...