Currently, the most successful Deep Learning architecture for large language models is the transformer. The attention mechanism of the transformer is equivalent to modern Hopfield networks, therefore is an associative memory. However, this associative memory has disadvantages like its quadratic complexity with the sequence length when mutually associating sequences elements, its restriction to pairwise associations, its limitations in modifying the memory, its insufficient abstraction capabilities. The memory grows with growing context. In contrast, recurrent neural networks (RNNs) like LSTMs have linear complexity, associate sequence elements with a representation of all previous elements, can directly modify memory content, and have high abstraction capabilities. The memory is fixed independent of the context. However, RNNs cannot store sequence elements that were rare in the training data, since RNNs have to learn to store. Transformer can store rare or even new sequence elements, which is one of the main reasons besides their high parallelization why they outperformed RNNs in language modelling. I think that future successful Deep Learning architectures should comprise both of these memories: attention for implementing episodic memories and RNNs for implementing short-term memories and abstraction.