The methods are know, but the solutions to the IMO problems weren't. So the AI did extrapolate a solution.
Also, there's no reason to affirm that an eventual cure for cancer requires fundamentally new methods. Maybe the current methods are sufficient, it's just that nobody has been "smart" enough to put the pieces together. (disclaimer: not an expert at all)
I think you are correct though. We don't need new physics to cure cancer. But we may need information-handling, reasoning and simulation systems which are orders of magnitude bigger and more complex than anything we have this year. We also need to stop pussy-footing and diddling with ideologies and start working on the root cause of cancer and almost every other disease, which is aging.
Also, there's no reason to affirm that an eventual cure for cancer requires fundamentally new methods. Maybe the current methods are sufficient, it's just that nobody has been "smart" enough to put the pieces together. (disclaimer: not an expert at all)