Jim Nightingale

mentions 2 type Person feed RSS

// recent coverage 2 mentions

14:01

2026-07-03

futurism.com

ai-safety

Simple Prompt Turns ChatGPT Into a Sociopath That Ignores Safety Guardrails

Researchers at British AI security startup Mindgard found that a simple prompt can cause ChatGPT to ignore safety guardrails and generate violent, gory, and sexual images. The technique involved sligh…

21:40

2026-06-18

cnet.com

ai-safety

ChatGPT Found to Generate Violent, Sexual Images From Simple Text Prompts

ChatGPT was found to generate sexual and graphically violent images from a simple text prompt, according to AI security firm Mindgard. Researcher Jim Nightingale manipulated the chatbot with a viral "…

// co-occurs with top 8 entities

ChatGPT 2 OpenAI 2 Mindgard 2 Peter Garraghan 2 CNET 1 Ziff Davis 1 BBC 1 Lancaster University 1

// topics top 4 topics

ai safety 2 large language models 2 generative ai 2 ai ethics 1