its lovely training data. no detection? add to training set -_-.
its also kind of laughable that somehow people are trying to prevent the outputs not to be altered. Asif you cannot manually paraphrase anything you can read. So the only solution would be, to make it utterly unreadable (which is not possible, it obviously defeats the purpose of the thing).
Not to mention local models ofcourse :-)
I think what we’re testing for here is LPM output that hasn’t even been skimmed by a human, let alone paraphrased.