"Intelligence" being what, math? Coding? Unfortunately there's a billion use cas... | Hacker News

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

deaux 35 days ago | parent | context | favorite | on: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cy...

"Intelligence" being what, math? Coding? Unfortunately there's a billion use cases for LLMs whose performance is not at all captured by the popular benchmarks they're all trying to maxx.

whimsicalism 35 days ago [–]

if you are relying on a model for a business process, it should be simple enough to benchmark on that process

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