AI chatbots’ safeguards can be easily bypassed, say UK

All five systems tested were found to be ‘highly vulnerable’ to attempts to elicit harmful responses

Guardrails to prevent artificial intelligence models behind chatbots from issuing illegal, toxic or explicit responses can be bypassed with simple techniques, UK government researchers have found.

The UK’s AI Safety Institute (AISI) said systems it had tested were “highly vulnerable” to jailbreaks, a term for text prompts designed to elicit a response that a model is supposedly trained to avoid issuing.