There are always ways to trade precision for speed in computer statistics models... | Hacker News

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

		fwungy on July 8, 2023 \| parent \| context \| favorite \| on: Experiencing decreased performance with ChatGPT-4 There are always ways to trade precision for speed in computer statistics models.

afro88 on July 8, 2023 [–]

Sure, generally speaking. Is that true for static, fixed parameter count LLMs like GPT4?

I think you're hand waving a lot just to claim that OpenAI are (somehow) reducing accuracy of their models during high load. And I'm not sure why.

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