Implications of Quantum Computing for Artificial Intelligence alignment research
This addresses AI alignment researchers by suggesting that quantum computing may not be a priority for overcoming current challenges, indicating an incremental perspective.
The paper argues that quantum computing is unlikely to help solve current bottlenecks in AI alignment, based on claims that it leads to compute overhang rather than algorithmic overhang and that quantum measurement issues do not invalidate major assumptions in alignment research, with some exceptions like tripwiring and adversarial blinding.
We explain some key features of quantum computing via three heuristics and apply them to argue that a deep understanding of quantum computing is unlikely to be helpful to address current bottlenecks in Artificial Intelligence Alignment. Our argument relies on the claims that Quantum Computing leads to compute overhang instead of algorithmic overhang, and that the difficulties associated with the measurement of quantum states do not invalidate any major assumptions of current Artificial Intelligence Alignment research agendas. We also discuss tripwiring, adversarial blinding, informed oversight and side effects as possible exceptions.