It took Andrew Wiles 7 years of intense work to solve Fermat's Last Theorem.
The METR institute predicts that the length of tasks AI agents can complete doubles every 7 months.
We should expect it to take until 2033 before AI solves Clay Institute-level problems with 50% reliability.
There is an ongoing effort to formalize a modern, streamlined proof of FLT in Lean, with all the needed prereqs. It's estimated that it will take approx. 5 years, but perhaps AI will lead to some meaningful speedup.
If you have a sufficiently strong verifier 1/100000 reliability is already enough
That's exactly why the Millennium Prize Problem Bench[1] was created.
1. https://mppbench.com/