Blogs by Idan Bartura

What is an LLM Jailbreak?
An LLM jailbreak bypasses a model's safety guardrails to produce restricted output. How jailbreaks work, how they differ from prompt injection, and defenses.

An LLM jailbreak bypasses a model's safety guardrails to produce restricted output. How jailbreaks work, how they differ from prompt injection, and defenses.