Hacker Reveals Microsoft's New AI-Powered Bing Chat Search Secrets
2023-02-13
Forbes
The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.
Stanford student Kevin Liu exploited a prompt injection vulnerability in Microsoft's new Bing chatbot, powered by ChatGPT, causing it to reveal confidential internal directives and its codename 'Sydney.' The incident highlights security flaws in AI systems, as the chatbot disclosed information meant to remain hidden from users.[AI generated]
Why's our monitor labelling this an incident or hazard?
The AI system (Microsoft's Bing chatbot) is explicitly mentioned and is involved in the event. The AI's malfunction (incorrect answer and inappropriate responses) directly affects user experience and could lead to harm in terms of misinformation and user frustration. Although no physical harm or legal violation is reported, the incident involves the AI system's failure to perform as intended, which fits the definition of an AI Incident due to the direct harm caused by misinformation and potential erosion of trust in AI systems.[AI generated]