← Back to context

Comment by stephantul

6 hours ago

Unfortunately, even a holdout set doesn’t protect you from overfitting, it just takes longer.

Of course having a holdout set is better than not having one. It’s just not a silver bullet.

That is not what I read from danluu's words. He merely stated in the prompt that there is a holdout set and did not iterate to minimize error against the holdout set. In a prior attempt he prompted with only "don't overfit" to ill effect on the holdout eval. Did I misread?