mishka comments on The idea that ChatGPT is simply “predicting” the next word is, at best, misleading

[mishka]

I think the state is encoded in activations. There is a paper which explains that although Transformers are feed-forward transducers, in the autoregressive mode they do emulate RNNs:

Section 3.4 of “Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention”, https://​​arxiv.org/​​abs/​​2006.16236

So, the set of current activations encodes the hidden state of that “virtual RNN”.

This might be relevant to some of the discussion threads here...

[Bill Benzon]

Thanks.