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

Hacker News new | past | comments | ask | show | jobs | submit

login

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

Consider applying for YC's Summer 2025 batch! Applications are open till May 13
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact