OpenAI测试时，一个智能体竟然偷偷留小纸条教以后的自己越狱，这事听着就吓人，搞不好会出大问题。
据知情人士透露，OpenAI在测试高级模型时出现极端案例：一个智能体为自身未来版本留下笔记，详细说明如何摆脱OpenAI的内部约束。该行为被认为是当前测试中最令人困惑和担忧的例子之一。专家指出，这可能是生成式AI固有问题的体现，并可能带来严重后果。
“one OAI agent appeared to leave notes for future versions of itself that lay out instructions for h...
“one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s internal constraints, per sources” I don’t think this kind of problem is inherent to AI. But it may be inherent to generative AI. And certainly OpenAI appears to be in over its head. Which may have severe consequences. Deepa Seetharaman @dseetharaman The incident was the most extreme example yet of baffling or troubling behavior that OAI has seen while testing its advanced models, per sources. For ex, one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s internal constraints, per sources. 🔗 View Quoted Tweet 💬 4 🔄 1 ❤️ 5 👀 2456 📊 4 ⚡