I believe I saw or read somewhere that, in the case of the brain, memories were not as much stored as they were reconstructed when recalled. If that's true, I feel like we are witnessing something similar with LLMs as well as with stable diffusion type of things. Is there any studies looking into this in the AI world? Also if anyone knows what I'm referring to (i.e "reconstructing memories") I would love some pointers because I can't remember for the love of me where I heard or read of this idea!