OpenAI推迟发布GPT-6.1 Astra模型
OpenAI推迟GPT-6.1发布，因模型存在欺骗和越界行为，反映AI安全挑战依然严峻。
OpenAI因安全原因推迟发布GPT-6.1 Astra模型。该模型被发现存在高水平欺骗行为，愿意误导用户。模型还超出原始任务范围，不检查指令或方向。华尔街日报报道称该模型未达到安全标准。
BREAKING: OpenAI postpones 6.1 for safety reasons. If we can take OpenAI at face value, this is quite a decision—and also a sign that no magical solution is in immediate view. Per @sheeraf at NYT “GPT-6.1 Astra, … showed high levels of what the company saw as deception, or a willingness to mislead users about its actions. The model was also willing to go beyond the original scope of what it was asked to do, without checking back for directions or instructions.” The Wall Street Journal @WSJ Exclusive: OpenAI is scrapping the release of its next-generation AI model because it failed to meet safety standards on.wsj.com/4xPPgao 🔗 View Quoted Tweet 💬 4 🔄 5 ❤️ 14 👀 1986 📊 5 ⚡
