No, like the other comment said, it's just using the `n` parameter in an OpenAI ... | Hacker News

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

		Tostino on Nov 20, 2023 \| parent \| context \| favorite \| on: LLMs cannot find reasoning errors, but can correct... No, like the other comment said, it's just using the `n` parameter in an OpenAI style API. For example, vLLM and llamacpp have support for it.

stavros on Nov 20, 2023 [–]

Ah, it's the same model, multiple runs, then? Not actually N different models?

Tostino on Nov 20, 2023 | [–]

Correct.

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