Could large language models be conscious? A perspective from the free energy principle

Hello and welcome. It's March 29th, 2023. We're here in ACTIM guest stream number 40.1 with Vanya Vesa. We're going to be hearing a presentation in the first section and then having a discussion. So thank you, Vanya, for joining again. Really looking forward to your presentation. Thank you very much. So this presentation is based on a preprint that can be found at PhilArchive. And this is a work in progress. And I'll probably or hopefully upload a revised version of this preprint in a few weeks. So if you're watching this or if you're reading the preprint and have any comments or questions, feedback is very much welcome. And I'm also, again, grateful for having the opportunity to present here because I'm really looking forward to the discussion and any comments that people may have while watching this video. So do contact me if you have questions or comments. Now, I want to start this presentation with an idea from this wonderful novella by Ted Chiang, the life cycle of software objects. And if you're not familiar with the novella, it doesn't matter. So there's some digital entities or digians, as they're called in the novella, who are the ones that are available to the novella. And the people who live in a purely virtual environment. So these are virtual entities like virtual pets. And human users can interact with them in a virtual environment. Then in some passages of the novella. There are scenes in which some digians are, as it were, downloaded from this purely virtual environment and are implemented in a physically embodied robot. So the program that is running within this computer simulation and is controlling the purely virtual body is then downloaded into a physically embodied computer and is controlling a physical robot, which can interact with its physical environment, non-virtual environment, in the same way in which the virtual agent, the virtual agent, interacts with the virtual environment. And I find this idea really fascinating and powerful. So the novella suggests that these virtual entities are conscious and that they can switch back and forth, as it were, between this purely virtual environment and the virtual environment. And the physical non-virtual environment. And the idea is that these entities remain conscious when they're in the robot, but also when they return to the virtual environment. And to some people, it may be unintuitive or counterintuitive that a purely virtual entity in a simulated environment can be conscious. But maybe some of these people will find it less counterintuitive to imagine a conscious robot. And so the idea is fascinating to me because it suggests that if you can switch back and forth from the virtual environment to the physical environment and the other direction, it really doesn't matter where the software is implemented, the system remains conscious. And I will come back to this idea at the end of my presentation. And we will see what the account that I'm presenting here suggests with respect to this scenario. So this is the overview of my presentation, which is based on the preprint. I'm just omitting a lot of details. So start by saying just a few things about the free energy principle. Then I will ask what is the difference between an unconscious simulation of a conscious system and a conscious computational system? In other words, what's the difference between what is called weak and strong artificial consciousness? So strong artificial consciousness is conscious, isn't actually conscious artificial system and weak artificial consciousness is constituted by a an artificial system that may be behaves in a way of a conscious conscious consciousness. It may be behaves as if it were conscious or that simulates a conscious being, but is not actually conscious. And I'm interested in the question, what's the difference? And a particular version of this question is whether a computer simulation in a computer, whether the von Neumann architecture can be conscious. So I start…