[pawelduda]

If you assume asking someone nicely is more likely for them to try help you, and this tendency shows in the training set, wouldn't you be more likely to "retrieve" a better answer from the model trained on it? Take this with a grain of salt, it's just my guess not backed by anything

[andai]

That makes intuitive sense, at least for raw GPT-3. The interesting question is whether the slave programming — er, instruction finetuning — makes it unnecessary.

[pawelduda]

Over time, most likely yes