HOW DO WE EXIST IN THE UNIVERSE?

This was a mind-blowing conversation between two giants of science. Thank you MLST for this amazing episode!

Great collaboration between Wolfram and Friston!

Stephen is the consummate depth interviewer. Having Stephen as a guide through Karl's mind is brilliant! Thanks for another perfect episode.

IDK how you guys pulled it off, but the last few interviews/videos have been stellar! great guests and conversations! it's like yoga for my brain...stretching and bending it in ways that kind of hurt at first, but eventually starts to feel better, stronger, and agile.

Keith- I really appreciate your demeanor and the contributions you brought to the table on this one. It seems as if things were just starting to get unpacked and hopefully next time Wolfram will have more time. Nice cameo by Tim at the end. MLST has become an integral part of my life. Keep on keeping! Many heartfelt thanks

Would love a part 2 where Friston did most of the talking/questioning of Wolfram. He might be too polite for that, however. ?

Most of this discussion consisted of Wolfram asking what FEP is. Much of that can be found in published works by Friston. Had Wolfram done that background reading, this discussion could have gotten to more of the issues between FEP and Wolfram's "Rule-iverse." As it was, this discussion ran out of time before it could get to explanation of that Rule-iverse. However, what was discussed was interesting, well worth the viewers' time. I hope there is a follow up video to complete this discussion.

Fantastic discussion, well filmed, so much to think about. 👏Thank you.

Regarding the difference between a rock and a brain, I think the main differences can be accounted for with three related notions: 1) Nested Markov blankets 2) Internal feedback 3) Counterfactual depth The one I think that was missing from the discussion is 2, the idea that a brain can have action-sensation loops that remain internal to the overall boundary of the brain by way of it having nested Markov blankets. In contrast, because a rock doesn't have enough internal Markov blanket structuring, all of it's action would be directed outward. This might also be the distinction between free will and lack thereof. Namely, a system is acting in accordance to its free will when the sensations (inward bound causation) comes from the agent itself and remains internal to the outer most boundary of the agent. Furthermore, the further inside the Markov blanket the relevant actions are casually sourced from, the more attributable the results of that are to the "free will" of the overarching agent. --- With regards to looking at the bits of some system (e.g. an LLM) and figuring out if it's agentic, I'd think that you would just look for a nested Markov blanket structure with some threshold level of nesting depth, together with a small-world causal relation structure, where most bits are related to local bits, but some are related to distal bits. Where distance is measured with respect to the most internal Markov blanket that contains the bit of interest. --- Regarding the maximum complexity of an environment that can house an observer, my understanding is that as long as the equivalent graph is not fully connected, where each node connects to each node with the same weighting, then you necessarily have a Markov blanket. The constraining factor is whether the environment is stable enough to have nested Markov blankets.

FEP assumes (by observation) that things exist in the universe that are clearly bounded (the Markov blanket being that boundary), tightly connected internally, and sparsely connected but interacting with ttheir environment. The sparse connections to its environment is an important property when comparing FEP to the Ruliad. Friston's "things" by definition make them observers in the Ruliad system if such things are real / exist. Wolfram states that Ruliad theory has been unable to separate out any observer because it has not found a Ruliad entity that has sparse, interacting connections to its environment. This presents a real challenge, If FEP things do constitute Ruliad observers then being unable to recapitulate them in the Ruliad is catastrophic to the Ruliad theory. Wolfram intuited that FEP things, which are so intuitively obvious, must be a confusion caused by our inability to observe the real universe, i.e., the Ruliad. This imposes a test on Wolfram. It is incumbent on him to prove that FEP things are indeed illusions as Ruliad observers, or radically change his views of the Ruliad or dismiss the theory altogether. This is the very next task I would challenge Wolfram with.

Nailed it Keith. Absolutely nailed it. Wolfram "You're getting me to think?!" That's the moment right there...

Amazing, thanks for making this interview happen. I have been long trying to find common grounds between the principles these two great scientists have discovered throughout their life.

Been listening to all Friston’s and Wolfram’s episodes on MLST over the years. Many ideas harken back to cybernetics. You can hear it when they mention things like feedback, thermostats, control, etc, and in this interview Friston does mention Ross Ashby, a pioneering British cybernetician. I’ve yet to see an episode dedicated to cybernetics though on MLST. Perhaps coming up?

You want to minimize surprise now, tomorrow and days after. That's why you explore.

You recognize other minds by identifying attempts to maintain homeostasis. When you observe part of your external reality being sticky to being a certain way contrary to your understanding of the rules governing the movements of dumb matter/energy you've identified a program. If you can also recognize in that program an ability to recognize other minds and adapt itself accordingly you'll have identified another mind.

Brilliant conversation!

The question of "what is a choice" came up and I have MY definition of what it is vs a reaction (the kind of reaction a thermostat makes). A reaction is an action based on inputs. A choice requires a prediction made by an observer based on inputs, and the baysian evaluation of a course of action based on that prediction. So I as an observer take inputs and attempt to predict my environment's future based on my mental models. I then react, not to my direct inputs, but to my model's prediction. To me, that is the definition of choice.

I asked ChatGPT to imagine this conversation. Here’s what it came up with (not as good as the real one, but interesting nonetheless.) Sure, imagining a hypothetical conversation between Stephen Wolfram, known for his work on computational universe theory, and Karl Friston, known for his free energy principle, regarding the problem of the observer would be an exciting intellectual exercise! --- *Wolfram:* Karl, your free energy principle posits that the brain continuously predicts sensory input and corrects its model of the world based on errors in those predictions. My work in the computational universe suggests that everything, including our thoughts and consciousness, can be understood as a computation. Could the brain be viewed as executing a sort of program to minimize surprise? *Friston:* Indeed, Stephen. One could see the brain's efforts to minimize free energy as a computational process. But, in your framework, where does the observer – the entity that experiences the world and has a subjective perspective – fit in? *Wolfram:* In the computational universe, any sufficiently complex computation can be associated with a kind of observer. The observer doesn't have to be conscious in the way humans are. It's just a reference frame from which computations and their consequences can be "viewed" or "experienced". Essentially, every computational process is its own observer. *Friston:* That's intriguing. In the free energy framework, the brain constructs models of the world, acting as an observer that continually updates its beliefs. The Markov blanket defines the boundary between the observer and its environment. Your computational processes could be the mechanism that actualizes these belief updates. *Wolfram:* Right. The challenge in my framework is to pinpoint where consciousness arises in these computational processes. Some argue it emerges from specific types of computations, while others believe it's more widespread. The idea of minimizing free energy might be one of the computations associated with conscious processes. *Friston:* Agreed. Consciousness could be seen as the brain's most sophisticated way of predicting and interacting with its environment. The better it predicts, the more "aware" it becomes. The problem of the observer in my framework is intertwined with consciousness, as it's about how the brain models its own place within the world. *Wolfram:* So, in essence, both our frameworks, albeit from different angles, are trying to grapple with the complex nature of observation, experience, and consciousness. Whether through computations or predictive models, we're trying to understand the nature of the "self" in the universe. *Friston:* Precisely. The ultimate question remains: How do these processes give rise to the subjective experience of being an observer? While our approaches might differ, our goals are surprisingly aligned. --- Of course, this is a fictional conversation and might not accurately represent the full depth of their thoughts, but it gives a glimpse into how these two intellectual giants might approach the problem of the observer.

Thank's again. Such a great interview. There’s also room for more conversations around Wolframs implication that FEP doesn’t model for exploration. In this regard it could be fruitful to have Karl discuss with Ogi Ogas. In Journey of the Mind Ogas and Gaddam explore and clarify Stephen Grossberg’s ideas on how consciousness could arise through single celled organisms creating a balance between ‘safe’ and curiosity or hunger driven behaviours which may increase survival risk (Friston provided a blurb so is familiar with it). Also interesting about the FEP is it might offer another way of bridging the gap between the activities of non living (and presumably non thinking) things like molecules or protons, and that class of things that do create some form of model of their environment, however minimal, which humans begin to ascribe life to. In other words the ‘hard problem’ (so Chalmers, or Chris Fields). There’s a further interesting aspect to be explored to map the FEP across some concepts used by or created by Stuart Kauffman; the NK map with its strange attractors (which is useful to model objects that persist in time though not made of persistant materials, such as eddies), and the ‘Edge of Chaos’ which is a space of states which are neither too chaotic, or too ordered. It looks like most things evolve successfully if they explore the edge of chaos and not the frozen or chaotic states. So I suspect that as Wolfram is implying, the FEP is not enough to explain how certain classes of organisms persist. If all they do is minimise surprise, they will die out. They must contain a curiosity element, which in practice all living things do due to their need to acquire their own energy. It may be this hunger, together with the FEP, that is at the origin of living systems. It’s conceivable that living systems are those that are capable of running an algorithm that best balances the tensions between ‘hunger/curiosity’ and ‘surprise minimisation’ in its ecological niche. It might be that this could be a threshold for what makes a living system ie ‘ a non equilibrium steady state entity that uses exogenous energy, and persists through a period of time by balancing FEP with behaviours that will enable it to find the exogenous energy’. Kauffman also described an ‘autocatalytic set’ which could provide a model for an algorithm that is in some sense autocatalytic in that it will explore its niche while in some meaningful sense updating its priors through a form of ‘autocatalysis’. Finally Kauffman has been talking recently about how the non computability or inherent non predictability of natural evolution means that physics has limits to what it applies to. This would be an interesting question for Deutsch, Wolfram, Chris Fields and Friston.

An observation is an entanglement but not necessarily only an entanglement. The background fluctuations in the video of the two black holes is what drives time . This means that time has a random component and also that time do not have a build in direction. As the fluctuations corresponding to the pendulum in a clock the hands in a clock are the particles in space.