Researchers Use AI to Jailbreak ChatGPT, Other LLMs

quot;Tree of Attacks With Pruning" is the latest in a growing string of methods for eliciting unintended behavior from a large language model.

AI researchers say they've found a way to jailbreak Bard and ChatGPT

Exploring the World of AI Jailbreaks

GPT-4 Jailbreak: Defeating Safety Guardrails - The Blog Herald

As Online Users Increasingly Jailbreak ChatGPT in Creative Ways, Risks Abound for OpenAI - Artisana

Prompt attacks: are LLM jailbreaks inevitable?, by Sami Ramly

Human resource management in the age of generative artificial intelligence: Perspectives and research directions on ChatGPT - Budhwar - 2023 - Human Resource Management Journal - Wiley Online Library

Using AI to Automatically Jailbreak GPT-4 and Other LLMs in Under a Minute — Robust Intelligence

Computer scientists claim to have discovered 'unlimited' ways to jailbreak ChatGPT - Fast Company Middle East

Microsoft-Led Research Finds ChatGPT-4 Is Prone To Jailbreaking

I Had a Dream and Generative AI Jailbreaks

US Researchers Demonstrate a Severe ChatGPT Jailbreak