A recent paper (van Rooij et al. 2024) claims to have proved that achieving human-like intelligence using learning from data is intractable in a complexity-theoretic sense. We point out that the proof relies on an unjustified assumption about the distribution of (input, output) tuples in the data. We briefly discuss that assumption in the context of two fundamental barriers to repairing the proof: the need to precisely define ``human-like," and the need to account for the fact that a particular machine learning system will have particular inductive biases that are key to the analysis. Another attempt to repair the proof, by focusing on subsets of the data, faces barriers in terms of defining the subsets.

翻译：近期论文（van Rooij 等，2024）声称已证明：从数据中学习以实现类人智能在复杂性理论意义上是不可行的。我们指出，该证明基于一个关于数据中（输入，输出）元组分布的不合理假设。我们简要讨论了该假设在修复该证明时面临的两个根本障碍：需要精确定义“类人智能”，以及需要考虑特定机器学习系统具有对分析至关重要的特定归纳偏置这一事实。另一种尝试通过关注数据子集来修复证明的方法，则在定义子集方面面临障碍。