Unlike previous models aimed at solving specific problems, FunSearch combines a large language model called Codey with other systems to suggest, evaluate and improve solutions.
The researchers wrote the problem in Python, leaving out lines that describe the solution approach, and FunSearch filled in the gaps by providing code to solve the problem. After reviewing millions of suggestions, FunSearch successfully found the correct solution to a complex math problem. Additionally, the vehicle demonstrated its versatility by solving the container packaging problem, an important problem in computer science, and finding solutions faster than human-developed methods.
This breakthrough proves that large language models, when properly controlled, can not only produce text but also actively participate in solving complex mathematical problems.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
