A. I. Algebraic Geometry Algebra/Logic DeLong Diversity Functional Analysis Grad Algebra/Logic Homotopy Init Conditions Kempner Lie Theory Math Club Math Phys Noncomm Geometry Number Theory PDE/Analysis Probability Rep Theory Grad Student Seminar Thesis Defenses Topology Ulam Math Edu

Events for AI Seminar

ICS calendar file for A. I.

This file can be used to add scheduled events to your calendar, however every program is unique. Below you will find what information is available, but if nothing else works try creating a new calendar in your program and using

http://math.colorado.edu/seminars/ics/ai.ics

as the source.

Thunderbird

Seminar on issues relating to AI and mathematics, for a general mathematical audience.

Fri, Sep. 4 1:25pm (Math 3…	Edgar Costa (MIT) X Large language models become more reliable when surrounded by well-designed instructions, reusable skills, persistent records, and independent checks. I will explain how to build and use these supporting structures for rigorous technical work. How to Tame Your LLM: Harnesses for Rigorous Work
Fri, Sep. 11 1:25pm (Zoom (…	Ken Ono (Axiom Math) X Mathematics is entering a period of both promise and unease. AI systems now discover counterexamples and conjectures, produce research-level arguments, and generate formally verified proofs in systems like Lean. This talk offers a working map of the landscape, organized around three distinct modes: discovery, reasoning, and verification, and why confusing them is the fastest way to overclaim. After surveying recent landmarks, I will present case studies from my own work at Axiom Math. I will discuss what is real, what is hype, and how rigor survives. The speaker is on Zoom. We suggest you attend on zoom (better experience for the speaker). Math 350 will be available for those who wish to share in-person viewing. Mathematics in the Age of AI: Discovery, Verification, and the Future of Proof
Fri, Sep. 18 1:25pm (Math 3…	Gregory Berkolaiko (Texas A&M) X Claude Code is a command-line AI assistant that reads and edits files directly in a project directory. This talk reports on using it for three tasks: (a) reading a paper in an unfamiliar area and writing a report on it, a task often faced by a student; (b) revising a paper draft; and (c) course preparation, specifically the design of student projects. For (a) we work through "Bakry-Émery curvature on graphs as an eigenvalue problem" by Cushing, Kamtue, Liu and Peyerimhoff (Calc. Var. PDE, 2022). The second half concerns guardrails: writing a rules file the assistant is expected to follow, keeping the human as the decision-maker on every edit, and tracking changes through git and Overleaf. We will see cases where the assistant caught errors a careful reader would miss, cases where it introduced errors of its own, and cases where it simply ignored an explicit instruction. The talk is an introduction, aimed at those who have not yet used Claude Code or a comparable tool (Cursor, Aider). Math editing with Claude Code: uses and guardrails
Fri, Sep. 25 1:25pm (Math 3…	Sachi Hashimoto X New technologies often change our tools before they change the way we work. Large language models can now produce convincing mathematical code very rapidly through mathematical "vibe coding" (prompting AI and then accepting code if it seems to work). But when this code is intended for use in a publication or inclusion in a database, the stakes are higher: errors in the code become errors in the mathematical literature. Is the alternative to "vibe coding" reading the code line-by-line? I will talk about how we can build software development workflows for the AI age. Starting from the basics of version control and Git, and assuming no prior experience, I will discuss iterative AI-assisted development, subagents, code review, testing, and continuous integration. The talk will be aimed at mathematicians interested in developing large-scale mathematical software and databases without giving up oversight and trust. AI-Assisted Coding for Mathematicians: How to Build Software Without Vibe Coding
Fri, Oct. 2 1:25pm (Math 3…	TBA TBA
Fri, Oct. 9 1:25pm (Math 3…	Zak Miller TBA
Fri, Oct. 23 1:25pm (Math 3…	Mike Mulligan (University of California Riverside) TBA
Fri, Oct. 30 1:25pm (Math 3…	Matt Grimes (Amazon) TBA
Fri, Oct. 30 1:25pm (Math 3…	TBA TBA
Fri, Nov. 6 1:25pm (Math 3…	Mohammed Abouzaid (Stanford) X In the past year AI systems have produced genuine research results in mathematics. What is much less clear is how to measure what these systems can actually do, and how to use them in one's own work. I will describe First Proof, which tests AI systems against unpublished mathematics, research mathematicians contribute problems with known but unpublished proofs, and the systems' solutions are refereed and graded, and report what successive batches of this have taught us. AI as a scientific instrument for mathematics
Fri, Nov. 13 1:25pm (Math 3…	Lionel Levine (Cornell University) TBA
Fri, Nov. 20 1:25pm (Math 3…	TBA TBA
Fri, Dec. 4 1:25pm (Math 3…	Emily Riehl (Johns Hopkins University) TBA

Main menu

Search

Other ways to search:

Events for AI Seminar