analiza aiqbench
This small qualitative study (N=10, diary plus interviews) finds that people who use several multimodal LLMs build informal hierarchies among them, shift those rankings by context, and switch models based on task, effort, latency, and perceived credibility. The sample is too small to generalize, but the findings point to real friction in multi-model workflows, including prompt portability, inconsistent behavior, and fragmented chat histories. For AI readers, the practical signal is that coordination across models is becoming a user-experience problem in its own right.
One Is Not Enough: How People Use Multiple AI Models in Everyday Life
arXiv:2603.26107v1 Announce Type: cross Abstract: People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-platform practice creates coordination challenges: adapting prompts to different interfaces, calibrating trust against inconsistent behaviors, and navigating separate conversation histories. Prior HCI research focused on single-agent interactions, leaving multi-MLLM orchestration underexplored. Through a diary study and semi-structured interviews (N=10), we examine how individuals organize work across competing AI systems. Our findings reveal that users construct primary and secondary hierarchies among models that shift over usage context. They also develop personalized switching patterns triggered by task aggregation to adjust effort and latency, and output credibility. These insights inform future tool design opportunities, supporting users to coordinate multi-MLLM workflows.
Abstract:People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-platform practice creates coordination challenges: adapting prompts to different interfaces, calibrating trust against inconsistent behaviors, and navigating separate conversation histories. Prior HCI research focused on single-agent interactions, leaving multi-MLLM orchestration underexplored. Through a diary study and semi-structured interviews (N=10), we examine how individuals organize work across competing AI systems. Our findings reveal that users construct primary and secondary hierarchies among models that shift over usage context. They also develop personalized switching patterns triggered by task aggregation to adjust effort and latency, and output credibility. These insights inform future tool design opportunities, supporting users to coordinate multi-MLLM workflows.
Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
arXiv:2603.26107 [cs.HC]
(or arXiv:2603.26107v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2603.26107 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 210 cuvinte
Subiecte conexe
Koopman Theory and Metaethics
LessWrong · 19 sept. 2026
How bad would it be if GPS satellites were shot down?
LessWrong · 12 iun. 2026
Will Robotics Have a ChatGPT Moment?
IEEE Spectrum · 20 mai 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026