As highlighted e.g. at Human Compatible by Stuart J. Russell (2019), this AI alignment intrinsically linked to the idea of utility in economy.
There are two main ways to try and reach AGI:Which one of them to take is of of the most important technological questions of humanity according to Ciro Santilli
- AI training robot: expensive, slow, but realistic world
- AI training game: faster, less expensive, but possibly non-realistic-enough realistic
There is also an intermediate area of research/engineering where people try to first simulate the robot and its world realistically, use the simulation for training, and then transfer the simulated training to real robots, see e.g.: realistic robotics simulation.