OpenAI 公布 722 篇由未发布内部模型产出的数学论文
源：https://t.co/B9DaaF3jAW
OpenAI 把一个没发布的模型的数学作业晒出来了：722 篇论文、372 组结果，每题烧 3 小时 Pro 算力，看看推理模型解题水平到哪了。
OpenAI 发布了由一个未公开的内部模型生成的 722 份数学手稿，整理为 372 组相关结果。这批手稿来自约 4,000 道研究级数学题的评估，每个结果平均消耗 3 小时 ChatGPT Pro 级别的思考算力。发布内容包括论文、证明工件和部分推理摘要，但模型本身仍未开放。
源：https://t.co/B9DaaF3jAW
源： x.com/kimmonismus/st… Chubby♨️ @kimmonismus HOLY, the rumors were true: OpenAI has published 722 mathematical manuscripts produced by an *unreleased* internal model. The collection groups them into 372 families of related results, drawn from an evaluation involving approximately 4,000 research problems. OpenAI says the standard procedure used an average of three hours of ChatGPT Pro thinking compute per result. The release includes papers, proof artifacts and selected reasoning summaries. The model itself remains unreleased. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 198 ⚡