Hacker News new | ask | show | jobs
Measuring What Matters: Construct Validity in Large Language Model Benchmarks (oxrml.com)
3 points by Cynddl 230 days ago
2 comments
ammaox 230 days ago
A very large review of AI benchmarks that reveals a worrying trend in their effectiveness and scientific rigor
link
jruohonen 227 days ago
Also Register picked it:

https://www.theregister.com/2025/11/07/measuring_ai_models_h...

link