Human–AI Collaboration at Scale: Task Criticality, Agency, and Friction across 250,000 Conversations
About Event
🔬 AI4Science on alphaXiv
🗓 Friday October 2nd 2026 · 10 AM PT
🎙 Featuring Yijia Shao
💬 Casual Talk + Open Discussion
🎥 Zoom: Upon Registration
Description:
AI is increasingly embedded in professional work, yet how people actually collaborate with it at scale remains poorly understood. Drawing on a corpus of 249,834 real-world conversations, we conduct privacy-preserving analysis by asking three questions: what work people bring to AI, what roles humans retain in completing that work, and where human-AI collaboration breaks down. We find that users bring to AI not only trivial tasks but also consequential, hard-to-reverse work, with high criticality delegation concentrating in advisory and professional domains. As stakes rise, users engage more actively with AI output, and conversation length nearly doubles from ephemeral to high-stake tasks. We then examine human agency, the degree of control and responsibility users retain in completing the task. Human-led collaboration dominates overall, but users construct their level of agency through how they prompt and iterate. Across different levels of agency lies a common tension: does working with AI build human capability, or substitute for human effort? We examine this tension through AI-supported learning and upskilling, finding that active teaching is common (67% of conversations) but its benefits are unevenly realized. We further show that friction arises in roughly half of all conversations but it is often productive, and users often employ active strategies to recover from friction when it does occur. Together, these results map how humans and AI work together at scale and when that collaboration makes people more capable, and when it doesn’t.
Whether you’re working on the frontier of LLMs or just curious about anything AI4Science, we’d love to have you there.
Read the paper here! https://www.alphaxiv.org/pdf/2608.human-ai-collaboration-at-scale
Hosted by alphaXiv