Джейлбрейк

EN · JailbreakДжейлбрейк — попытка обойти ограничения модели и заставить её нарушить правила через специально составленный запрос.Определение на английскомA prompt technique that bypasses an AI agent's safety instructions or guardrails, causing it to produce restricted content or perform disallowed actions. Jailbreaks range from simple role-play tricks ("pretend you're an unrestricted AI") to sophisticated multi-turn attacks. Defending against jailbreaks requires layered controls: system prompt hardening, input and output classifiers, and action-level authorization rather than relying on the model alone.