Counteract Homogenization with Diversity

Resist statistically-common ideas; deploy diverse specialist personas and, where feasible, multiple models with different training data. A single LLM voice narrows the collective idea space even as it may improve individual idea quality.

  • Anderson et al. (2024, PNAS Nexus): LLMs matched individual human originality scores but AUT variability was 0.459 (LLM) vs. 0.699 (human) — structurally convergent at population level
  • Meincke/Nave/Terwiesch (Nature Human Behaviour, June 2025): across 5 experiments, 37 of 45 comparisons showed ChatGPT decreases population-level idea diversity; 94% of AI-assisted ideas shared overlapping concepts
  • MultiAgent Research Ideator (SIGDIAL 2025, 7,000 ideas empirically): diverse agent personas are the single highest-leverage variable for idea quality, outperforming parallelism or iteration depth
  • Always ask "what would be the most surprising version of this?" to reach the low-probability tail of the idea distribution rather than the statistical center
  • Prefer genuine multi-model diversity (different providers, different training data) over multi-prompt diversity within one model where feasible
version
1.0.0
status
draft
tags
brainstorming, diversity, ai-pitfalls
author
Mike Fullerton
modified
2026-06-27
references
Anderson et al., PNAS Nexus, 2024, https://academic.oup.com/pnasnexus/article/5/3/pgag042/8529001Meincke/Nave/Terwiesch, Nature Human Behaviour, June 2025, https://www.nature.com/articles/s41562-025-02173-xMultiAgent Research Ideator, SIGDIAL 2025, arXiv 2507.08350

Change History

Version Date Author Summary
1.0.0 2026-06-27 Mike Fullerton Initial creation