Glossary
Jailbreak
A user's attempt to make a model ignore its safety rules through crafted prompts.
Distinct from prompt injection, which is carried out by a third party through content the model processes.
Related terms
Prompt injectionStaged release
Get the brief in your inbox
One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.
Published daily by AI Briefing. We never share your address.