Yhn CultureTelevision first seen 2 d ago, last 13 min ago, peak #3

90% of US working hours poorly covered by AI benchmarks

Original: 90% of US working hours are spent on tasks not covered well by AI benchmarks

New analysis from Mercor's labor index finds that roughly 90% of hours worked in the United States are spent on tasks that existing AI benchmarks do not measure well. The finding suggests current evaluations of AI systems capture only a narrow slice of real workplace activity, raising questions about how well model performance claims translate to actual jobs.

Why now: It challenges common assumptions that AI benchmarks reflect how ready AI is to take on real work.

MercorUnited States

Open on hn →

Evidence

• 90% of US working hours are spent on tasks not covered well by AI benchmarks · speckx · 618

API: https://socialmediatrends-api.osmike.com/v1/trends/2510056