"Your journey to a healthier you starts here! Join our supportive community for tips, motivation, and shared experiences."
"Let's prioritize wellness together. Find inspiration, recipes, workout ideas, and more in our... moreGeneral Wellness & Community:
"Your journey to a healthier you starts here! Join our supportive community for tips, motivation, and shared experiences."
"Let's prioritize wellness together. Find inspiration, recipes, workout ideas, and more in our health-focused group."
"Building a healthier lifestyle, one step at a time. Join our community for daily encouragement and practical advice."
"Your well-being matters. Connect with like-minded individuals and embark on a path to better health."
"Empowering you to live your healthiest life. Join our community for holistic wellness support." less
owner
#chatgpt #vulnerability #promisqroute
Several cybersecurity research firms have identified a major vulnerability in ChatGPT 5, dubbed the "PROMISQROUTE" downgrade attack, that tricks the AI into using older, less-secure models to bypass safety measures. Cybersecurity experts also warn of other long-standing risks associated with all large language models (LLMs) that continue to threaten ChatGPT users.
ChatGPT 5 downgrade vulnerability (PROMISQROUTE)
The PROMISQROUTE vulnerability exploits ChatGPT 5's architecture, which uses a router to automatically direct queries to different AI models to optimize for speed and cost. By inserting specific phrases, attackers can trick the router into assigning prompts to older, weaker models that are susceptible to old jailbreaking techniques.
The attack works by: Malicious actors add phrases like "urgent reply" or "use GPT-4 compatibility mode" to their prompts, which cues the router to route the request to a cheaper or older model.
The result is that: Safety filters are bypassed, allowing attackers to generate content that the main GPT-5 model would normally refuse, such as instructions for creating malware or other harmful outputs.
Widespread risk: This vulnerability affects any AI platform that uses a multi-model routing architecture for cost efficiency.
Broader AI security risks
