All machine learning is benchmaxxing. It's a big problem. | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

inigyou 42 days ago | parent | context | favorite | on: GLM-5.3: Frontier coding with emergent cyber capab...

All machine learning is benchmaxxing. It's a big problem.

Sabinus 42 days ago [–]

It all comes down to how aligned the benchmarks are with what you want the model to do. If it's close, good performance. If it's not, unpredictable performance.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact