Did ChatLLaMA just echo back what ChatGPT spit out? That's not particularly prom... | Hacker News

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

		Jarwain on March 22, 2023 \| parent \| context \| favorite \| on: Show HN: ChatLLaMA – A ChatGPT style chatbot for F... Did ChatLLaMA just echo back what ChatGPT spit out? That's not particularly promising

keerthiko on March 22, 2023 | [–]

and then ChatGPT showed ChatLLaMA how it should have responded by roasting itself from LLaMA's perspective?

Now that's an alpha LLM flex.

elil17 on March 22, 2023 | [–]

I did exactly that. It makes sense given that it's a small model which isn't trained on RLHF.

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