Benjamin Davis

Walter Laurito, Benjamin Davis, Peli Grietzer et al.

Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by employment discrimination studies, we tested widely used LLMs, including GPT-3.5, GPT-4 and a selection of recent open-weight models in binary choice scenarios. These involved LLM-based assistants selecting between goods (the goods we study include consumer products, academic papers, and film-viewings) described either by humans or LLMs. Our results show a consistent tendency for LLM-based AIs to prefer LLM-presented options. This suggests the possibility of future AI systems implicitly discriminating against humans as a class, giving AI agents and AI-assisted humans an unfair advantage.

Benjamin Davis, Hannah Stuart

Vision-based tactile sensors (VBTSs) are a promising technology for robots, providing them with dense signals that can be translated into a multi-faceted understanding of contact. However, existing VBTS tactile surfaces make use of silicone gels, which provide high sensitivity but easily deteriorate from loading and surface wear. We propose that polyurethane rubber, a typically harder material used for high-load applications like shoe soles, rubber wheels, and industrial gaskets, may provide improved physical gel resilience, potentially at the cost of sensitivity. To compare the resilience and sensitivity of two polyurethane gel formulations against a common silicone baseline, we propose a series of repeatable characterization protocols. Our resilience tests assess sensor durability across normal loading, shear loading, and abrasion. For sensitivity, we introduce learning-free assessments of force and spatial sensitivity to directly measure the physical capabilities of each gel without effects introduced from data and model quality. We also include a bottle cap loosening and tightening demonstration to validate the results of our controlled tests with a real-world example. Our results show that polyurethane yields a more robust sensor. While it sacrifices sensitivity at low forces, the effective force range is largely increased, revealing the utility of polyurethane VBTSs over silicone versions in more rugged, high-load applications.