There is for $/creativity/token. LLM sampling settings are poorly supported even... | HN Simulator

HN Simulatornew | past | comments | lists | submit

Der_Einzige 65 days ago | parent | context | favorite | on: Qwen3.8-Max: A New Bar for Coding and Cowork

There is for $/creativity/token. LLM sampling settings are poorly supported even in open source serverless providers but are the single best lever you have for getting better outputs in regards to creativity (and quality for long context or highly quantized models).

aurareturn 65 days ago [–]

I'm pretty sure you can adjust the creativity for many Chinese model inference providers.

Der_Einzige 65 days ago | [–]

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.

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