Maryna Viazovska, one of the most extraordinary mathematicians to emerge in recent years, captured the public’s attention last July 2022. She was awarded the coveted Fields Medal for her transformative research on the sphere-packing problem in eight and twenty-four dimensions. This time-honored mathematical problem examines how closely similar circles and spheres can be packed into n-dimensional space. In doing so, Viazovska’s solutions shed light on this intricate puzzle. They certainly did unlock exciting new possibilities for collaboration between human mathematicians and AI.
What Viazovska did was incredible. In her work, she showed that this E8 symmetric arrangement is indeed the best packing configuration in eight dimensions. She was joined by other mathematicians to investigate the Leech lattice. Jointly, they determined it to be the most efficient packing arrangement in twenty-four dimensions. These achievements have paved a runway for deeper exploration into the relationship between mathematics and technology.
The Role of AI in Mathematical Proofs
Sidharth Hariharan was instrumental in the formalization of Viazovska’s sphere-packing proofs. For him, it was through this process that he began to develop a productive disposition toward making sense of deeper mathematical concepts. “So it was a pretty fruitful collaboration,” Hariharan remarked about the synergy between human effort and AI technology.
That fruitful collaboration produced an AI system called Gauss, which successfully autoformalized Viazovska’s proof of a spheres-packing arrangement in twenty-four dimensions. Within only two weeks, Gauss had processed more than 200,000 lines of code. This accomplishment highlights AI’s remarkable power for solving complex mathematical verification problems. It autoformalized the eight-dimensional proof in only five days. It even managed to catch a typo in the original published paper too!
“When they reached out to us in late January saying that they finished it, to put it very mildly, we were very surprised.” – Sidharth Hariharan
The speed at which Gauss progresses brings about a seismic change in the field of mathematics. Jesse Han, CEO and co-founder of Math, Inc., spoke recently about the development of Gauss. This AI is both agent-based and reasoning-driven, combining entertainment-oriented natural-language reasoning with state-of-the-art fully formalized reasoning. This combined ability makes it double as powerful at checking intricate math proofs.
“It’s a particular kind of language model called a reasoning agent that’s meant to interleave both traditional natural-language reasoning and fully formalized reasoning.” – Jesse Han
The Significance of Formal Verification
The formal verification of mathematical proofs is vital to the establishment of those proofs credibility and correctness. According to Liam Fowl, a mathematician who has been following this development closely, “Formal verification of a proof is like a rubber stamp.” This intensive step-by-step procedure guarantees that each element of the proof stands the test of examination.
“Mathematicians working together with a powerful AI is a great example of the new, transformative age of mathematical research,” Han pointed out. This unique human insight, with AI mass and efficiency, leads to unprecedented accuracy and speed in validating incredibly complex proofs.
“These new results seem very, very impressive, and definitely signal some rapid progress in this direction.” – Liam Fowl
The formalization project first took shape around a design made by Hariharan and his partners. For the next 15 months or so, they continued developing the project’s repository in private until June 2025, when public access was allowed. All these studies laid the groundwork that Gaia was able to build on, giving Gauss the raw material to work from.
“We had been building the project’s repository for about 15 months when we enabled public access in June 2025.” – Sidharth Hariharan
Future Implications for Mathematics
As opportunities for what AI can do continue to amaze us, so do its potentials for application within mathematics research. Han emphasized that technology like Gauss could empower mathematicians by allowing them to focus more on creative problem-solving rather than administrative tasks associated with proof verification.
“I think the end result of technology like this will be to free mathematicians to do what they do best, which is to dream of new mathematical worlds.” – Jesse Han
The intersection of mathematics and artificial intelligence has produced the greatest turning point for academic researchers in the field to date. This fruitful collaboration between Viazovska’s mathematical insight and AI’s computational power is a harbinger of things to come where such partnerships are the norm. This evolution has the potential to unlock new advances in mathematics. Beyond refining our theoretical understanding, it will make practical applications much more effective across various scientific disciplines.