Re:Ten advances in mathematics and theoretical computer science
by Readerium on Saturday August 01, 2026 @10:59PM
(#49140639)
Exactly, this is an example of "Reward Hacking", that is too common in a lot of cases.
Another case I want to highlight is writing GPU kernels as illustrated by the following example:
Say I want to generate random number with Normal (0, 1) distribution.
Often times the AI written kernel will just generate the number 0. The tests often fail to catch these errors.
Another case I want to highlight is writing GPU kernels as illustrated by the following example: Say I want to generate random number with Normal (0, 1) distribution. Often times the AI written kernel will just generate the number 0. The tests often fail to catch these errors.