Subscribe to Events

The main drawback of using generative AI for advanced mathematics via Large Language Models (LLM) is that they are probabilistic pattern-matchers, not logical reasoning engines. However,  LLMs can pick up on patterns in higher mathematics that are difficult for humans to see. By putting the design of LLMs to their advantage, mathematicians may use them as powerful interactive assistants that can carry out laborious tasks, generate and debug code, check examples, formulate conjectures and more. We discuss how LLMs can be used to advance mathematics research by careful use of prompt engineering. We also discuss the integration of LLMs with a formal proof assistant such as Lean.

Zoom link: https://rutgers.zoom.us/j/93921465287
Meeting ID: 939 2146 5287
Passcode: 196884, the dimension of the weight 2 homogeneous subspace of the moonshine module