---
id: llm-evolution-and-meta-optimization/07-what-nobody-has-done-yet
title: 'LLM evolution and meta-optimization: 7. What nobody has done yet'
report: https://ai.hiina.space/reports/llm-evolution-and-meta-optimization.md
section: 7
version: 1
updated: '2026-10-27'
author: Hiina
---

Index of everything on this site: https://ai.hiina.space/index.md

# LLM evolution and meta-optimization: 7. What nobody has done yet

- Section 7 of 10 of the report "LLM evolution and meta-optimization" by Hiina (v1, updated 2026-10-27)
- Report overview and contents: https://ai.hiina.space/reports/llm-evolution-and-meta-optimization.md
- Previous: https://ai.hiina.space/reports/llm-evolution-and-meta-optimization/06-family-trees-the-instruments-exist-but-nobody.md
- Next: https://ai.hiina.space/reports/llm-evolution-and-meta-optimization/08-five-experiments-cheapest-first.md

## 7. What nobody has done yet

These are gaps this review's searches found. "Not found" reflects the limits of a few dozen targeted searches, not proof of absence.

- **Full-tuple genomes.** No work evolves architecture, data mix, hyperparameters, adapters and harness together, with trained weights inherited across generations. Every system evolves one layer: merge recipes, LoRA populations, PBT hyperparameters, or agent code. Data mix has no evolutionary treatment in anything found here.
- **Speedrun log as evolutionary search.** The modded-nanogpt README is a dated, attributed, categorized record of 92 selections, with cross-track transfer and labelled AI-System entrants. No published analysis treats it as a fitness-landscape walk: gain by mutation category, feature survival, contributor networks, human versus agent contribution.
- **Price-equation and multilevel analysis of the Hugging Face ecosystem.** Laufer et al. measure inheritance and drift of metadata traits but exclude merges and adapters. No one has partitioned trait change into selection and transmission terms, or into within-family and between-family components, using downloads or descendants as fitness.
- **Harness genealogy.** Nothing systematic exists on the lineage of coding-agent harnesses or system prompts.
- **A multi-signal typed genealogy.** Declared, structural, weight and behavioural evidence have never been combined with per-edge confidence, and there is no ground-truth benchmark for distillation edges.
- **Lineage distance versus trait transfer.** Subliminal learning is reported as same-base versus different-base. Nobody has tested whether output-based or weight-based phylogenetic distance predicts graded transfer.
- **Lab and market ecology.** No data-driven model treats labs, funding, talent mobility or architecture adoption as an evolutionary system; the only rigorous treatment is qualitative philosophy.
- **Permutation-aligned merging of independently pretrained LLMs.** Demonstrated for vision networks only; nothing found for LLMs.
- **Independent replications.** Learned optimizers at scale, ES beating GRPO beyond Countdown, and evolved merges beating hand-tuned ones all rest mainly on the proposing authors.
- **Swarms as colonies, and the selected-versus-inherited unit gap.** No work maps multi-agent systems on shared weights to eusocial or clonal biology, or measures the persona-versus-weights mismatch.

---

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space