Anthropic banned about 11.4M Claude accounts in H1 2026
According to an Anthropic report released in July, the company banned roughly 11.4 million Claude accounts in the first half of 2026, received about 398,000 appeals and granted about 42,000 of them. The report did not disclose a complete breakdown of ban reasons, and these figures alone cannot show whether recent bans have increased, but the appeal outcomes have drawn attention to the platform's enforcement standards and review process. Cited violations include using the service for illegal activity, privacy infringement and breaches of regional usage limits; Anthropic also says it filed more than 15,000 reports with child-safety organizations in the same period, and it has revised its Claude usage policy to bar repeated extreme cruelty toward the model without an obvious purpose from Nov. 12, saying that users expressing dissatisfaction, pushing back at the model, creating dark-themed content, and model testing or research fall outside the ban.
Large-scale bans and the accompanying policy tightening directly affect whether developers and businesses can rely on Claude, and put the platform's appeal and review standards in the spotlight.

陶哲轩提出「数学 2.0」:AI 解题之外,还要帮助人理解证明
10 月 11 日,数学家陶哲轩公开了在加州理工学院的演讲《数学 2.0》。他认为,AI 正在降低部分数学问题的求解成本,使数学研究逐渐从「证明稀缺」走向「证明富足」。但目前多数前沿问题仍未解决,不能只凭公开传播的成功案例判断 AI 的整体能力。

陶哲轩指出,得到正确证明,并不意味着研究者理解了证明为何成立,或掌握了可用于其他问题的新方法。他主张用 AI 寻找更易理解的证明、整理分散的研究成果,并对大量数学问题开展系统分析。例如,等式理论项目通过人类与自动化工具协作,对超过 2200 万个命题作出了判定。