We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato's concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.

翻译：我们认为，人工智能模型（尤其是深度网络）中的表示正在趋于收敛。首先，我们综述了文献中多个收敛实例：随着时间的推移并跨越多个领域，不同神经网络表示数据的方式正变得越来越一致。其次，我们证明了跨数据模态的收敛现象：随着视觉模型和语言模型规模的扩大，它们度量数据点间距离的方式也变得越来越相似。我们假设这种收敛正推动形成一种共享的现实统计模型，类似于柏拉图提出的理想实在概念。我们将此类表示称为柏拉图式表示，并探讨了导致其产生的若干可能选择压力。最后，我们讨论了这些趋势的影响、其局限性以及我们分析的反例。