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 41 days 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 41 days ago | [–]

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

MagicMoonlight 41 days 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