发表机构
Imperial College London（帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文借鉴种群遗传学，将多代AI模型训练类比为有性与无性繁殖，验证了赖特-费雪过程等机制，并提出融合遗传与费雪-穆勒效应，为AI继承提供预测框架。
AI 中文摘要
人工智能发展的某些方面类似于一个群体过程，在此过程中，模型被特化、在同行输出上重新训练，或通过平均权重进行组合。这些实践导致了生物学意义上（由种群遗传学研究的）的模型世代。在此，我发展了这一平行关系，并根据有性繁殖和无性繁殖来解读多代模型群体，正式地将这两个领域重新结合。我在一个精确的遗传模型、训练好的网络（循环、前馈和变分自编码器生成器）以及大型语言模型中测试了这些类比，并表明它们在总体上成立，但存在一些可测量的特定于架构的偏差。已知在模型输出上递归训练会导致模型崩溃，这一过程先前被描述为类似于遗传漂变；我发展了其后的一切。一个在其父代输出上重新训练的学习者的最小模型精确地再现了赖特-费雪过程；每一代添加的经过验证的真实数据扮演了移民的角色，令人惊讶的发现是，真实数据样本的绝对数量而非其比例才是重要的，这与种群遗传学完全一致。在父母输出的平均值上训练子代会抵消拥有多个父母的好处，这与融合遗传相匹配（并复活了詹金对达尔文的反对意见），而组合父母使得每个父母保留其最强贡献则保持了这一好处；合并的语言模型专家在所有随机种子中超过了每个父母（费雪-穆勒效应）；当谱系学习了冲突的约定时，它们会变得生殖隔离，失去合并的能力，而不仅仅是漂移分离。随着人工智能社会在时间上和空间上都成为社会，其遗传的数学框架获得了预测能力。值得注意的是，该框架几乎可以整体从生物学中改编而来。
英文摘要
Some aspects of AI development resemble a population process in which models are specialised, retrained on the output of peers, or combined by averaging weights. These practices lead to generations of models, in the biological sense studied by population genetics. Here, I develop this parallelism and interpret multigenerational model populations in terms of sexual and asexual reproduction, formally recombining the two fields. I test these analogies in an exact inheritance model, in trained networks (recurrent, feedforward and variational autoencoder generators) and in large language models, and show that they hold generally, with some measurable architecture-specific biases. Training recursively on model output is known to lead to model collapse, a process previously described as akin to genetic drift; I develop all that follows. A minimal model of a learner retrained on its parent's output reproduces the Wright-Fisher process exactly; verified real data added to each generation play the role of immigration, with the surprising finding that the absolute number of real data samples matters, not their share, exactly as in population genetics. Training a child on the average of its parents' outputs cancels the benefit of having several parents, matching blending inheritance (and reviving Jenkin's objection to Darwin), whereas combining parents so that each keeps its strongest contribution preserves it; merged language-model specialists exceeded every parent across seeds (the Fisher-Muller effect); and lineages become reproductively isolated, losing the ability to merge at all, when they have learned conflicting conventions and not when they have merely drifted apart. As AI societies become societies in time as well as in space, a mathematical framework for their inheritance acquires predictive power. Remarkably, that framework can be adapted almost wholesale from biology.
Comments22 pages, 5 figures, 1 table. Supplementary Information (26 pp) and a plain-language figure appendix for readers from biology (23 pp) are included as ancillary files. Code, configs and seeds: https://git.lab.gilest.ro/giorgio/MachineSex
