top | item 45266092 (no title) samfriedman | 5 months ago Accuracy is a useless statistic: give us precision and recall. discuss order hn newest henryl|5 months ago Recall 91.5, F1 93.3 paradite|5 months ago I think you need to define which one is the positive, and which one is the negative?Is AI generated code the positive? LPisGood|5 months ago Useless is perhaps a but harsh. It tells you something. spott|5 months ago Only if you know the data distribution.It is pretty easy to get 99.99% accuracy on a dataset that is 99.99% a single class for example. dymk|5 months ago It tells me nothing because it doesn’t say if they mean precision or recall load replies (1)
henryl|5 months ago Recall 91.5, F1 93.3 paradite|5 months ago I think you need to define which one is the positive, and which one is the negative?Is AI generated code the positive?
paradite|5 months ago I think you need to define which one is the positive, and which one is the negative?Is AI generated code the positive?
LPisGood|5 months ago Useless is perhaps a but harsh. It tells you something. spott|5 months ago Only if you know the data distribution.It is pretty easy to get 99.99% accuracy on a dataset that is 99.99% a single class for example. dymk|5 months ago It tells me nothing because it doesn’t say if they mean precision or recall load replies (1)
spott|5 months ago Only if you know the data distribution.It is pretty easy to get 99.99% accuracy on a dataset that is 99.99% a single class for example.
dymk|5 months ago It tells me nothing because it doesn’t say if they mean precision or recall load replies (1)
henryl|5 months ago
paradite|5 months ago
Is AI generated code the positive?
LPisGood|5 months ago
spott|5 months ago
It is pretty easy to get 99.99% accuracy on a dataset that is 99.99% a single class for example.
dymk|5 months ago