2 papers
cs.CL2026
Invisible failures in human-AI interactions
Christopher Potts, Moritz Sudhof
AI systems fail silently far more often than they fail visibly. In an analysis of 100K human-AI interactions from the WildChat dataset, we find that 79% of AI failures are invisibl…
cs.CL2026
A paradox of AI fluency
Christopher Potts, Moritz Sudhof
How much does a user's skill with AI shape what AI actually delivers for them? This question is critical for users, AI product builders, and society at large, but it remains undere…