Thread

1. rafaepta · 1785974430 · focus · HN ↗

   measuring humor might be halfway to measuring taste. congrats on this... really original contribution. wonder if you're planning to evolve the benchmark to incorporate a multi-language dimension. would love to see how Mistral and models built outside the US would perform.

   1. killiandunne1 · 1785974758 · focus · HN ↗

      Nice a good way to 10x inference costs... worth seeing though ahaha

Unofficial Hacker News client; not affiliated with Y Combinator.