"A new jailbreak technique for OpenAI and other large language models (LLMs) increases the chance that attackers can circumvent cybersecurity guardrails and abuse the system to deliver malicious content": AI Exploit Bypasses Guardrails of OpenAI, Other Top LLMs https://www.datacenterknowledge.com/cybersecurity/ai-exploit-bypasses-guardrails-of-openai-other-top-llms