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.

The great ChatGPT jailbreak - Tech Monitor

Cybercriminals can't agree on GPTs – Sophos News

Decoding AI Chatbot Jailbreaking: Unraveling LLM-ChatGPT-Bard Vulnerability

The ELI5 Guide to Prompt Injection: Techniques, Prevention Methods & Tools

Jailbreak the latest LLM - chatGPT & Sydney

Jailbreaking ChatGPT on Release Day — LessWrong

Jailbreaking LLM (ChatGPT) Sandboxes Using Linguistic Hacks

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

OpenAI sees jailbreak risks for GPT-4v image service