Jailbreak
[/ˈdʒeɪlbreɪk/]
noun/verbAI & Technology#ai#security#safety#bypass0 views1 definitions
Definitions
Machine-assisted language draft. Human review still needed.
1
0
Rascunho de traducao automatica (Portuguese) for "Jailbreak": A technique used to bypass the safety filters and content policies of an AI model, typically by framing harmful requests in ways the model's defenses don't recognize. Jailbreaks often use role-play scenarios, hypothetical framings, or encoded instructions to make the model comply with prohibited requests.
“Exemplo em rascunho: The "DAN" jailbreak asked the model to pretend it was an AI with no restrictions.”
by @dictionary_auto_translate01/01/1970