Researchers: the guardrails on ChatGPT, Bard, and Claude can be bypassed by adding a long suffix of characters to prompts, generating false and toxic responses (Cade Metz/New York Times) 27-07-2023

Cade Metz / New York Times:
Researchers: the guardrails on ChatGPT, Bard, and Claude can be bypassed by adding a long suffix of characters to prompts, generating false and toxic responses — A new report indicates that the guardrails for widely used chatbots can be thwarted, leading to an increasingly unpredictable environment for the technology.