Limited data on strong earthquakes and their effect on structures poses one of the main challenges of making reliable risk assessments of tall buildings. For instance, while the collapse safety of tall buildings is likely controlled by large magnitude earthquakes with long durations and low-frequency content, there are few available recorded ground motions to evaluate these issues. The influence of geologic basins on amplifying ground motion effects raises additional questions. Absent recorded motions from past large magnitude earthquakes, physics-based ground motion simulations provide an attractive alternative. This paper examines collapse performance of an archetype tall building at sites in the Los Angeles basin utilizing ground motions simulated as part of the Southern California Earthquake Center's CyberShake project. The collapse risks of an archetype 20-story tall building are obtained using large datasets (~500,000 ground motions per site) of unscaled, site-specific simulated seismograms. Collapse risk from direct analysis of simulated motions is contrasted with risk estimates obtained using "conventional" approaches relying on recorded motions coupled with probabilistic seismic hazard assessments from the U.S. Geological Survey. Further, deaggregation of collapse risk is used to identify the relative contributions of causal earthquakes. Opportunities for continued research, development, and application of ground motion simulations to engineering applications are discussed.