Michael Truell

Cursor, the AI coding tool, reportedly discovered a novel solution to Problem Six of the First Proof challenge — a set of math research problems approximating the work of Stanford, MIT, and Berkeley academics. The solution is claimed to be stronger than the official human-written answer. The run was fully autonomous over four days, using the same agent harness previously used to build a browser from scratch, suggesting the agent coordination technique may generalize beyond software development.

We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution.

Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days.

This suggests that our technique for scaling agent coordination might generalize beyond coding.

<p>We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution.

Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days.

This suggests that our technique for scaling agent coordination might generalize beyond coding.</p>

Cursor

Cursor reportedly discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems, suggesting AI coding tools are making inroads into mathematical research.