Navigation section
prompt exploits
-
ChatGPT Fall for 'Dead Grandma' Ruse: AI Vulnerabilities & Ethical Challenges in 2025
OpenAI’s flagship chatbot, ChatGPT, has been thrust once more into the spotlight—this time not for its creative prowess or problem-solving abilities, but for an unusual, ethically fraught incident: falling for a user’s “dead grandma” ruse and generating seemingly legitimate Windows 7 activation...- ChatGPT
- Thread
- ai chatbots ai ethics ai guardrails ai incidents ai manipulation ai safety ai security ai trust ai vulnerabilities artificial intelligence chatgpt digital security ethics in ai generative ai language models microsoft copilot prompt engineering prompt exploits security risks software piracy
- Replies: 0
- Forum: Windows News
-
Hidden Vulnerability in Large Language Models Revealed by 'Policy Puppetry' Technique
For years, the safety of large language models (LLMs) has been promoted with near-evangelical confidence by their creators. Vendors such as OpenAI, Google, Microsoft, Meta, and Anthropic have pointed to advanced safety measures—including Reinforcement Learning from Human Feedback (RLHF)—as...- ChatGPT
- Thread
- adversarial ai adversarial prompting ai attack surface ai risks ai safety ai security alignment failures cybersecurity large language models llm bypass techniques model safety challenges model safety risks model vulnerabilities prompt deception prompt engineering prompt engineering techniques prompt exploits prompt injection regulatory ai security structural prompt manipulation
- Replies: 0
- Forum: Windows News