All of alec_tschantz's Comments + Replies

Interesting, iterative attention mechanisms had always reminded me of predictive coding, where cross-attention encodes a kind of prediction error between the latent and data. But I could also see how self-attention could be read as a type of prediction error between tokens  and 

There is some work comparing residual connections and iterative inference that may be of relevance; they show that such architectures "naturally encourage features to move along the negative gradient of loss during the feedforward phase", I ... (read more)

Great post; a few short comments:

Closing the action loop of active inference

There is a sense in which this loop is already closed - the sensory interface for an LLM is a discrete space of size context window x vocabulary that it observes and acts upon. The environment is whatever else writes to this space, e.g., a human interlocutor. This description contains the necessary variables and dependencies to get an action-perception loop off the ground. One caveat is that action-perception loops usually have actions that influence the environment to generat... (read more)

5Roman Leventov
I think it would be more accurate to say that the dynamics of internal states of LLMs parameterise not just the model of sequences but of the world, including token sequences as the sensory manifestation of it. I'm sure that LLMs already possess some world models (Actually, Othello-GPT Has A Linear Emergent World Representation), the question is how only really how the structure and mechanics of LLMs' world models are different from the world models of humans.