> So, in practice, inference computes a very rich vector of state- at each layer, for each token.
And that state is... internal to the neural network. My point here is there is no continuous state that is not computed from the context.
> This is also true about a human brain. My brain isn't going anywhere- it can't move by itself. It's also easy to kill (without the rest of my body, it dies in minutes!)
Your brain continues to run without sensory input. LLMs do not.
And that state is... internal to the neural network. My point here is there is no continuous state that is not computed from the context.
> This is also true about a human brain. My brain isn't going anywhere- it can't move by itself. It's also easy to kill (without the rest of my body, it dies in minutes!)
Your brain continues to run without sensory input. LLMs do not.