Adam K Dean

Posts tagged with prompt-injection

From Einstein to Turing: Misdirecting GPT-4 with Hidden Prompts

Published 19 May 2023 in artificial-intelligence with tags prompt-engineering , prompt-injection , prompt-hijacking , gpt , gpt-4 , security , openai , ai-experiments , research , machine-learning , language-models A recent discussion on Hacker News, titled "Let ChatGPT visit a website and have your email stolen," brought to light potential vulnerabilities in OpenAI's ChatGPT model, especially concerning its new web browsing capabilities. This stimulated an interest in understanding more about these vulnerabilities and how they could impact the reliability and integrity of information provided by the AI. Continue reading …



Newer Page 1 of 1 Older