Mathematical discoveries from program search with large language models
doi:10.1038/s41586-023-06924-6
Agents, open-endedness, AGI · 2023-12-14
Complete cleaned Markdown · Source Markdown including bibliography
Read in parts
Contents
- Mathematical discoveries from program search with large language models
- Abstract
- Similar content being viewed by others
- ThoughtSource: A central hub for large language model reasoning data
- Detecting hallucinations in large language models using semantic entropy
- Understanding large language models demands distinguishing human projection from machine cognition
- Explore related subjects
- Main
- FunSearch
- Specification
- Pretrained LLM
- Evaluation
- Programs database
- Prompt
- Distributed approach
- Extremal combinatorics
- Cap sets
- Admissible sets
- Bin packing
- Discussion
- Methods
- Implementation details of FunSearch
- Distributed system
- Prompt building
- Evolutionary method and program selection
- Robustness
- Related work
- LLMs
- Genetic programming
- Program superoptimization and software engineering
- Data availability
- Code availability
- Supplementary information
- Supplementary Information (download PDF )
- Supplementary Data 1 (download ZIP )
- Rights and permissions
- About this article
- Cite this article
- Share this article
- Comments
- Associated content
- Large language models help computer programs to evolve
- Search
- Quick links
- nature.com footer links
- About Nature Portfolio
- Discover content
- Publishing policies
- Author & Researcher services
- Libraries & institutions
- Advertising & partnerships
- Professional development
- Regional websites