Daniel Litt is a professor of mathematics at the University of Toronto. He has been a careful observer of AI’s progress toward accelerating mathematical discovery, sometimes skeptical and sometimes enthusiastic.  Topics we cover: the hardest problems models can solve today, whether there is convincing evidence that AI is speeding up math research, and what’s missing before AI might have a shot at solving Millennium Prize problems. We also discuss how to measure progress in math, including Epoch AI’s new FrontierMath: <a href="https://epoch.ai/frontiermath/open-problems">Open Problems</a> benchmark which evaluates models on meaningful unsolved math research problems.

<description>
 &lt;p&gt;&lt;br&gt;Daniel Litt is a professor of mathematics at the University of Toronto. He has been a careful observer of AI’s progress toward accelerating mathematical discovery, sometimes skeptical and sometimes enthusiastic. &lt;/p&gt;&lt;p&gt;&lt;br&gt;Topics we cover: the hardest problems models can solve today, whether there is convincing evidence that AI is speeding up math research, and what’s missing before AI might have a shot at solving Millennium Prize problems.&lt;/p&gt;&lt;p&gt;&lt;br&gt;We also discuss how to measure progress in math, including Epoch AI’s new FrontierMath: &lt;a href="https://epoch.ai/frontiermath/open-problems"&gt;Open Problems&lt;/a&gt; benchmark which evaluates models on meaningful unsolved math research problems.&lt;br&gt;&lt;/p&gt;
 </description>

AI math capabilities could be jagged for a long time – Daniel Litt

Description