<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Projects :: Robert Lipshitz</title>
    <link>https://pages.uoregon.edu/lipshitz/projects/index.html</link>
    <description>Documentation site for bfh_python Bordered Heegaard Floer homology is an extension of Ozsváth-Szabó’s Heegaard Floer homology to 3-manifolds with boundary. It gives an algorithm for computing Heegaard Floer homology, by cutting a manifold into pieces. In this thesis, Bohua Zhan gave a significant refinement of that algorithm. He implemented both in a Python package, bfh_python (available as a PIP package here). His implementation is fast enough to often be useful in practice.</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <atom:link href="https://pages.uoregon.edu/lipshitz/projects/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Claude Code for the Working Mathematician</title>
      <link>https://pages.uoregon.edu/lipshitz/projects/claude/index.html</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>https://pages.uoregon.edu/lipshitz/projects/claude/index.html</guid>
      <description>Overview and getting started Overview This is a guide, based on my experiences, for using Anthropic’s Claude chatbots to help with the kinds of work research mathematicians do. To keep this focused, I will only discuss non-teaching work, mainly working on research papers and a little about bureaucratic work. This is not about using it to prove theorems or discover new mathematics: I have not found them useful for that, and their ability to mislead in those contexts is potentially harmful. Rather, I’m focusing on tasks for which I think almost all working mathematicians will find the tool useful—now, not in some uncertain future.</description>
    </item>
  </channel>
</rss>