1. Still no support for multiple losses. Models like VAEs cannot be idiomatically implemented. The second loss has to be 'hacked' in. Notice how in the official example for VAE, the kl_loss is computed using variables which are NOT available via the loss function (https://github.com/fchollet/keras/blob/master/examples/varia...)

2. It's still an input->output paradigm, rather than a {input, output}->loss paradigm which gives more flexibility.

These two issues are the main reason why I stick to slightly lower level APIs, even though I _want_ to use Keras.