This is the definition of training the model on it's own output. Apparently that... | Hacker News

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

		consp 4 months ago \| parent \| context \| favorite \| on: A small number of samples can poison LLMs of any s... This is the definition of training the model on it's own output. Apparently that is all ok now.

baby 4 months ago | [–]

I mean you're supposed to use RAG to avoid hallucinations

MagicMoonlight 4 months ago | [–]

Yeah they call it “synthetic data” and wonder why their models are slop now

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