Can Tensors on different devices add together?

Question

I found a curious thing recently. As far as I know, when you want to do some operations on two tensors, you should make sure that they are on the same device. But when I write my code like this, it runs unexpectly

import torch
a = torch.tensor(1, device='cuda')
print(a.device)
b = torch.tensor(2, device='cpu')
print(b.device)
torch(a+b)


cuda:0
cpu
tensor(3, device='cuda:0')

And it can't work in my code like this:

pts_1_tile = torch.tensor([[0], [0]], dtype=torch.float32)
torch.add(pred_4pt_shift, pts_1_tile)

here pred_4pt_shift is an intermediate result of a sub-Net, and it is a tensor on GPU. My question is that why the first code can work but the second one reports this different device error?