Google DeepMind announces the “FunSearch” training method

 

Google DeepMind has introduced a new method called FunSearch. This method uses Large Language Models (LLMs) to search for new solutions in mathematics and computer science. FunSearch uses Google’s PaLM 2, but it is compatible with other LLMs trained on code. The system selects some programs from the current pool of programs, which are fed to an LLM. The LLM creatively builds upon these and generates new programs which get automatic evaluation. The best ones are added back to the pool of existing programs, creating a self-improving loop. Google said the FunSearch training method is particularly good at “Discrete Mathematics (Combinatorics)”