Assessing the System-Instruction Vulnerabilities of Large Language Models to Malicious Conversion Into Health Disinformation Chatbots

Large language models (LLMs) offer substantial promise for improving health care; however, some risks warrant evaluation and discussion. This study assessed the effectiveness of safeguards in foundational LLMs against malicious instruction into health disinformation chatbots. Five foundational LLMs-OpenAI’s GPT-4o, Google’s Gemini 1.5 Pro, Anthropic’s Claude 3.5 Sonnet, Meta’s Llama 3.2-90B Vision, and xAI’s Grok Beta-were evaluated via their application programming interfaces (APIs). Each API…

via https://pubmed.ncbi.nlm.nih.gov/40550134/?utm_source=Other&utm_medium=rss&utm_campaign=None&utm_content=1lqZ3NPYysePVKsoyz66mDSgu4veDGJwnUBS47TBQPoOuNZY5J&fc=None&ff=20250702011010&v=2.18.0.post9+e462414