https://stackresearch.org/tags/genetic-algorithms/Recent content in Genetic Algorithms on Stack ResearchHugoen-usSun, 15 Mar 2026 00:00:00 +0000https://stackresearch.org/research/genetic-prompt-programming/Sun, 15 Mar 2026 00:00:00 +0000https://stackresearch.org/research/genetic-prompt-programming/<p>A four-generation prompt evolution run moved average fitness from 0.887 to 0.926. The best prompt reached 0.965. The run used a population of 8 prompts and completed in under 4 minutes on a MacBook Pro with <code>llama3.1:8b</code> running locally through Ollama.</p> <p>The useful trick is not genetic programming in the old sense of random token edits. Mutation and crossover are language-model calls. Every variant is still a valid prompt. The model rewrites prompts in ways a human prompt engineer might recognize: tighter wording, added constraints, reordered instructions, more concrete examples, removed weak parts.</p>