LLaMA isn't built on RLHF, so it may be necessary to create a more extensive pro... | Hacker News

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

		RoboTeddy on March 10, 2023 \| parent \| context \| favorite \| on: Llama.cpp: Port of Facebook's LLaMA model in C/C++... LLaMA isn't built on RLHF, so it may be necessary to create a more extensive prompt. For example: ``` You are a super intelligent honest question-answering system. Q: What's 2+2? A: 4 Q: What color is the sky? A: ```

guestbest on March 11, 2023 [–]

This is Commodore 64 tier answers

lgas on March 12, 2023 | | [–]

That's the point, even C64 tier examples in one shot or few shot learning do wonders for changing the behavior of the model.

circuit10 on March 12, 2023 | | [–]

That's just an example

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