joelsimon.net/lluminate
joelsimon.net · 2,471 words · saved by 4 readers
An evolutionary algorithm for creative exploration.
Lluminate Creative Exploration with Reasoning LLMs Large Language Models (LLMs) generate coherent text but tend to produce homogeneous outputs when prompted for creative content. To overcome this, I introduce Lluminate, an LLM based evolutionary algorithm that explores diverse creations by combining evolutionary methods with principled creative thinking strategies. The findings demonstrate that integrating evolutionary pressure with formalized creative strategies enables sustained open-ended exploration (illumination) of latent creative spaces, offering new possibilities for assisted creative
saved by
related reading
- LLM Daydreaming · Gwern.netgwern.net
- Being creative requires taking riskshenrikkarlsson.xyz
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- Contra Labs - Powered by Contracontralabs.com
- Automating creativity - by Ethan Mollick - One Useful Thingoneusefulthing.org
- Modifying Large Language Model Post-Training for Diverse Creative Writingarxiv.org
- Open-endedness: The last grand challenge you’ve never heard of – O’Reillyoreilly.com
- Creativity Has Left the Chat: The Price of Debiasing Language Modelsarxiv.org
- The AI Picbreeder Experiment: In Search of Automatic Open-Endednesspub.sakana.ai
- Scaffolding Recursive Divergence and Convergencein Story Ideationarxiv.org
- Measuring LLM Novelty As The Frontier Of Original And High-Quality Outputarxiv.org
- MacGyver: Are Large Language Models Creative Problem Solvers?arxiv.org