Hacker News new | past | comments | ask | show | jobs | submit
aurareturn | on: Qwen3.8-Max: A New Bar for Coding and Cowork
I'm pretty sure you can adjust the creativity for many Chinese model inference providers.
Der_Einzige | parent
Most of them don't expose more than top_p/top_k/temperature. Those are woefully inadequate compared to what open source inference engines support.