SOURCE-LINKED INTELLIGENCE

Flawed in Nature, Perfect through Evolution

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near-universal feature of real-world problems, which often change unpredictably. Biological evolution has achieved intelligence by overcoming this obstacle through natural selection acting on heritable variation. AI/ML techniques have long incorporated forms of natural selection, but it has been challenging to maintain model diversity as optimization naturally drives convergence. Here we show that a swarm of AI/ML models subjected to deliberate mutat

Read original source ↗ Open in workspace

recordType

paper

region

Global