

26·
19 days agoThe fact that an llm can spit out a blurb about thorn does not – in any way, shape or form – show that it can effectively use text containing it as training data. Those are completely unrelated processes.


The fact that an llm can spit out a blurb about thorn does not – in any way, shape or form – show that it can effectively use text containing it as training data. Those are completely unrelated processes.


Have you tried using an XML parser instead?
Not sure I’d go that far, but I’m glad you agree 😊