Mesa-Optimization is the situation that occurs when a learned model (such as a neural network) is itself an optimizer. In this situation, a base optimizer creates a second optimizer, called a mesa-optimizer. The primary reference work for this concept is Hubinger et al.'s "Risks from Learned Optimization in Advanced Machine Learning Systems".
Example: Natural selection is an optimization process that optimizes for reproductive fitness. Natural selection produced humans, who are themselves optimizers. Humans are therefore mesa-optimizers of natural selection.
In the context of AI alignment, the concern is that a base optimizer (e.g., a gradient descent process) may produce a learned model that is itself an optimizer, and that has unexpected and undesirable properties. Even if the gradient descent process is in some sense "trying" to do exactly what human developers want, the resultant mesa-optimizer will not typically be trying to do the exact same thing.[1]
Previously work under this concept was called Inner Optimizer or Optimization Daemons.
Wei Dai brings up a similar idea in an SL4 thread.[2]
The optimization daemons article on Arbital was published probably in 2016.[1]
Jessica Taylor wrote two posts about daemons while at MIRI:
Some posts that reference optimization daemons:
"Optimization daemons". Arbital.
Wei Dai. '"friendly" humans?' December 31, 2003.