I can tell you that as someone who could have gotten bronze (i was too weak for the team) and is now a math phd--I would not have scored as well as alphaproof in three days most likely. In most problems either you find an idea soon or it can be much much longer. It's just not a matter of working and constant progress.
Noting the difference in humility between someone that has made the cut to participate in the IMO (6 people per country) and the multitude of retrospect prophets that trivialize the DeepMind achievement.
