← Back to context Comment by stavros 6 days ago They're using a revolutionary new method called "training on the test set". 2 comments stavros Reply drob518 6 days ago So, curve fitting the training data? So, we should expect out of sample accuracy to be crap? stavros 6 days ago Yeah, that's usually what tends to happen with those tiny models that are amazing in benchmarks.
drob518 6 days ago So, curve fitting the training data? So, we should expect out of sample accuracy to be crap? stavros 6 days ago Yeah, that's usually what tends to happen with those tiny models that are amazing in benchmarks.
stavros 6 days ago Yeah, that's usually what tends to happen with those tiny models that are amazing in benchmarks.
So, curve fitting the training data? So, we should expect out of sample accuracy to be crap?
Yeah, that's usually what tends to happen with those tiny models that are amazing in benchmarks.