Search for: All records

We present a novel prompting strategy for artificial intelligence driven digital avatars. To better quantify how our prompting strategy affects anthropomorphic features like humor, authenticity, and favorability we present Crowd Vote - an adaptation of Crowd Score that allows for judges to elect a large language model (LLM) candidate over competitors answering the same or similar prompts. To visualize the responses of our LLM, and the effectiveness of our prompting strategy we propose an end-to-end framework for creating high-fidelity artificial intelligence (AI) driven digital avatars. This pipeline effectively captures an individual's essence for interaction and our streaming algorithm delivers a high-quality digital avatar with real-time audio-video streaming from server to mobile device. Both our visualization tool, and our Crowd Vote metrics demonstrate our AI driven digital avatars have state-of-the-art humor, authenticity, and favorability outperforming all competitors and baselines. In the case of our Donald Trump and Joe Biden avatars, their authenticity and favorability are rated higher than even their real-world equivalents. 

Abstract This study represents the first campaign‐style teleseismic shear wave splitting (SWS) investigation of central Myanmar, an area that is tectonically controlled by the oblique subduction of the Indian Plate underneath the Eurasian Plate. The resulting 678 well‐defined and 247 null SWS measurements obtained from recently deployed 71 broadband seismic stations show that the Indo‐Burma Ranges (IBR) possess mostly N‐S fast orientations that are parallel to the trend of the depth contours of the subducted slab. Relative to the global average of 1.0 s, extremely large splitting times with station‐averaged values ranging from 1.28 to 2.79 s and an area‐averaged value of 2.09 ± 0.55 s are observed in the IBR. In contrast, the Central Basin (CB) and the Shan Plateau (SP) are characterized by slightly larger than normal splitting times. The fast orientations observed in the CB are mostly NE‐SW in the northern part of the study area, N‐S in the central part, and NW‐SE in the southern part. The fast orientations change from nearly N‐S along the N‐S oriented Sagaing Fault, to NW‐SE in the central and eastern portions of the SP. These observations, together with SWS measurements using local S events, crustal anisotropy measurements using P‐to‐S receiver functions, and the estimated depth of the source of anisotropy using the spatial coherency of the splitting parameters, suggest the presence of a trench‐parallel sub‐slab flow system driven by slab rollback, a trench‐perpendicular corner flow, and a trench‐parallel flow possibly entering the mantle wedge through a slab window or gap.