Geordie Williamson, a mathematician on the University of Sydney, who worked on PatternBoost with Charton, has not yet tried Axplorer. But he’s curious to see what mathematicians do with it. (Williamson still occasionally collaborates with Charton on academic projects but says he isn’t otherwise connected to Axiom Math.)
Williamson says Axiom Math has made several improvements to PatternBoost that (in theory) make Axplorer applicable to a wider range of mathematical problems. “It stays to be seen how significant these improvements are,” he says.
“We’re in a wierd time in the intervening time, where a number of corporations have tools that they’d like us to make use of,” Williamson adds. “I’d say mathematicians are somewhat overwhelmed by the chances. It’s unclear to me what impact having one other such tool will likely be.”
Hong admits that there are a variety of AI tools being pitched at mathematicians without delay. Some also require mathematicians to coach their very own neural networks. That’s a turnoff, says Hong, who’s a mathematician herself. As an alternative, Axplorer will walk you thru what you need to do step-by-step, she says.
The code for Axplorer is open source and available via GitHub. Hong hopes that students and researchers will use the tool to generate sample solutions and counterexamples to problems they’re working on, speeding up mathematical discovery.
Williamson welcomes recent tools and says he uses LLMs quite a bit. But he doesn’t think mathematicians should throw out the whiteboards just yet. “In my biased opinion, PatternBoost is a beautiful idea, but it surely is actually not a panacea,” he says. “I’d love us to not forget more down-to-earth approaches.”
