GPT-6-Astra 在 TheoPhysEval 基准解出 50 道理论物理题中的 49 道
GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
OpenAI 的 GPT-6-Astra 在 TheoPhysEval 上做对了 50 道 unpublished 物理题里的 49 道，一题才 2.4 美元，连专家答案被它挑出错的桥段都值得看看。
在 TheoPhysEval 基准测试中，GPT-6-Astra 解出了 50 道未发表的理论物理计算题中的 49 道，准确度与领域顶尖专家相当，单题成本仅 2.40 美元。部分被判失败的题目，事后发现是专家参考答案本身有误。研究人员认为物理领域尚未出现类似数学领域的那种突破，原因是这类智能体缺乏"品味"。他们同时指出，这一结果已影响年轻物理学家的培养方式和该领域的机会公平。
GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
On the TheoPhysEval benchmark, GPT-6-Astra solves 49 of 50 unpublished theoretical physics calculations as accurately as leading specialists. In some cases where the agent seemed to fail, the experts' own reference solutions turned out to contain errors. But the researchers say physics hasn't had a breakthrough like the ones in mathematics, because the agents lack "taste." They still think autonomous, top-level AI research could arrive soon. They already see consequences for how young physicists are trained and for equal opportunity in the field. The article GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece appeared first on The Decoder .
