Exploiting floating point errors for free energy is a good one. And lots of cases where the problem wasn’t defined precisely enough, and the simulation solved it in a completely different way than was expected.
“Sometimes I think the surest sign that we’re not living in a computer simulation is that if we were, some microbe would have learned to exploit its flaws.”
Machine learning algorithms are not like other computer programs. In the usual sort of programming, a human programmer tells the computer exactly what to do. In machine learning, the human programmer merely gives the algorithm the problem to be solved, and through trial-and-error the algorithm has t…