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
- Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
- LLM Daydreaming · Gwern.netgwern.net
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms — Google DeepMinddeepmind.google
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Creativity Has Left the Chat: The Price of Debiasing Language Modelsarxiv.org
- Measuring LLM Novelty As The Frontier Of Original And High-Quality Outputarxiv.org
- Luma | AI Agents for Creative Worklumalabs.ai
- Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
- [2206.08896] Evolution through Large Modelsarxiv.org
- [2309.16797] Promptbreeder: Self-Referential Self-Improvement via Prompt Evolutionar5iv.labs.arxiv.org
- Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org