Get the latest tech news
ChatGPT just (accidentally) shared all of its secret rules
Saying 'hi' revealed OpenAI's instructions until the company shut it down, but you can still find them
OpenAI has since shut down the unlikely access to its chatbot's orders, but the revelation has sparked more discussion about the intricacies and safety measures embedded in the AI's design. The main one is called v2, and the chatbot explained how it differs from the "more formal and factual communication style" of v1, which "focuses on providing detailed and precise information, often in a structured and academic tone." He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool.
Or read this on Hacker News