I think this works, not because LLMs have a "hallucination" dial they can turn d... | Hacker News

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

		COAGULOPATH on Sept 16, 2024 \| parent \| context \| favorite \| on: g1: Using Llama-3.1 70B on Groq to create o1-like ... I think this works, not because LLMs have a "hallucination" dial they can turn down, but because it serves as a cue for the model to be extra-careful with its output. Sort of like how offering to pay the LLM $5 improves its output. The LLM's taking your prompt seriously, but not literally.

Meganet on Sept 16, 2024 [–]

It could also mean that it has some weight which is 'hallucination' and leads to more diverse stories.

Ask an LLM what hallucination is, ask it to write a story with etc.

without zeroing out things, everything has and can have some impact

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