top | item 34890185 (no title) jbenjoseph | 3 years ago But even so, the human picks the prompts and only publishes the AI outputs they think read nicely. There is information gain even in that. discuss order hn newest throwanem|3 years ago At the moment that's probably true, but is it guaranteed to remain so? jbenjoseph|3 years ago Even so, I don't think there is any evidence that LLM performance degrades when it is trained on its own output, and there is no intuitive reason it should. load replies (1)
throwanem|3 years ago At the moment that's probably true, but is it guaranteed to remain so? jbenjoseph|3 years ago Even so, I don't think there is any evidence that LLM performance degrades when it is trained on its own output, and there is no intuitive reason it should. load replies (1)
jbenjoseph|3 years ago Even so, I don't think there is any evidence that LLM performance degrades when it is trained on its own output, and there is no intuitive reason it should. load replies (1)
throwanem|3 years ago
jbenjoseph|3 years ago