2025-05-14
It's incredible to me that a single system can contribute to numerous open problems in maths & CS (from faster matrix multiplication to sphere packing to analysis inequalities) AND improve Google's production infrastructure (data centers, TPU design, and AI training) (2/2) [image]
Google DeepMind
Google DeepMind unveils AlphaEvolve, a Gemini-powered AI coding agent that designs and optimizes advanced algorithms using an evolutionary framework
New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators
After 1.5 years of work, I'm so excited to announce AlphaEvolve - our new LLM + evolution agent! Learn more in the blog post: https://deepmind.google/... White paper PDF: https://storage.googleapis.com/ ... (1/2) [image]
Google DeepMind
Google DeepMind unveils AlphaEvolve, a Gemini-powered AI coding agent that designs and optimizes advanced algorithms using an evolutionary framework
New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators
2023-12-16
Excited to share our @nature paper on #FunSearch (Search in Functional space)! tl;dr: we find new results in maths by evolving code with a pretrained (no finetuning involved) medium-size LLM acting as crossover/mutation operator https://deepmind.google/... https://storage.googleapis.com/ ... 1/n [image]
MIT Technology Review
Google DeepMind's FunSearch model cracks the unsolved cap set problem in pure mathematics, the first time an LLM has solved a long-standing scientific puzzle
2023-12-15
Excited to share our @nature paper on #FunSearch (Search in Functional space)! tl;dr: we find new results in maths by evolving code with a pretrained (no finetuning involved) medium-size LLM acting as crossover/mutation operator https://deepmind.google/... https://storage.googleapis.com/ ... 1/n [image]
MIT Technology Review
Google DeepMind's FunSearch model cracks the unsolved cap set problem in pure mathematics, the first time an LLM has solved a long-standing scientific puzzle
outsmarting humans Maximilian Schreiner / The Decoder : Google DeepMind's FunSearch cracks mathematical puzzles with a LLM Davide Castelvecchi / Nature : DeepMind AI outdoes human ...