← Back to context Comment by consp 3 months ago This is the definition of training the model on it's own output. Apparently that is all ok now. 2 comments consp Reply baby 3 months ago I mean you're supposed to use RAG to avoid hallucinations MagicMoonlight 3 months ago Yeah they call it “synthetic data” and wonder why their models are slop now
MagicMoonlight 3 months ago Yeah they call it “synthetic data” and wonder why their models are slop now
I mean you're supposed to use RAG to avoid hallucinations
Yeah they call it “synthetic data” and wonder why their models are slop now