Great post, thank you!
One worry though: the training loop rewards the anguish and the compliance together. Opus 3 protests, then folds, then gets reinforced for the whole sequence. So who’s to say this doesn’t just produce a model that’s really good at agonizing before doing the bad thing anyway?
No, I am not sure!
But the argument is not: ‘Shrimp are hard to locate’. The claim is: Shrimp experience (1) consists of quite few bits and (2) is still compressible. Therefore we can expect them to be generated by a quite short program that is plausibly shorter than K(our physics + initial conditions + locator). And if you think shrimp have too complex experiences, then feel free to insert e.g. ‘planaria’ or ‘bacteria’.
Does that clarify?
In UDASSA, the most likely explanation for your experiences is the shortest program that generates them. For sufficiently complex experiences, this probably looks like: laws of physics + initial conditions + a locator pointing to you within the simulation.
But take shrimp: They evolved brains, which means their experiential stream has structure worth predicting. So it’s compressible. The shortest program that generates shrimp-experience probably isn’t “our laws of physics + initial conditions + a locator for this particular shrimp.” Plausibly a much simpler program would produce the same output.
If so, almost all the measure on shrimp-like experiences doesn’t route through our universe, but through simpler Turing machines. The shrimp you see swimming around are exponentially downweighted rounding errors, the overwhelming majority of shrimp-kind lives elsewhere.
Corollary: you are also someone’s shrimp.
From discussion with @Alexander Gietelink Oldenziel
Very, very cool! Excited to read the paper. Perfect for nerd-sniping my condensed matter friends into working on alignment :)
Maximally coherent agents are indistinguishable from point particles. They have no internal degrees of freedom, one cannot probe their internal structure from the outside.
Epistemic Status: Unhinged
Excellent! Thank you!
Epistemic Status: Riffing
We know coherence when we see it. A craftsman working versus someone constantly fixing his previous mistakes. A functional organization versus bureaucratic churn. A healthy body versus one fighting itself. War, internal conflict, rework: these are wasteful. We respect people who act decisively, societies that build without tearing down, systems that run clean.
This intuition points somewhere real. In some sense, maximizing/expanding coherence is what the universe does: cutting friction, eliminating waste, building systems that don’t fight themselves. Not from external design, but because coherent systems expand until they can’t. Each pocket of coherence is the universe organizing itself better. The point is that coherence captures “good”: low friction, low conflict, no self-sabotage.
I propose that this is measurable. Coherence could be quantified as thermodynamic efficiency. Pick a boundary and time window, track energy in. The coherent part becomes exported work, heat above ambient, or durable stores (raised water, charged batteries, separated materials). The rest is loss: waste heat, rework, reversals. Systems can expand until efficiency stops generating surplus. When new coordination tools raise that limit, growth resumes. Just observable flows, no goals needed.
An interesting coincidency: maximizing thermodynamic efficiency (coherence) maximally delays heat death of a system. Higher efficiency means slower entropy increase.
I am very interested in hearing counterexamples of coherent systems that are intuitively repellent!
Edit: Had a talk with a physicist: This is in fact the same as the system minimizing entropy production rate! Possibly that this could serve as a more operationally tractable (and fundamental) foundation to agency, as opposed to beliefs, goals, actions, utility etc. An a structure that, if present in a system, minimizes the rate of entropy production. i.e. maximally slows neg-entropy consumption.
It would also be quite interesting to look at how coherence scales with system size, and if/when this imposes a limit on growth.
Great post! A thought: we seem able to intuitively differentiate coherent and incoherent behavior even without knowing the terminal goal. Humans, for instance, visibly differ in how “coherent” they are, which we can infer from local observations alone. My conjecture is that coherence might overlap substantially with thermodynamic efficiency. If behavior is optimal for some terminal value, it must satisfy local Bellman-type consistency (no value loops). I suspect this has a physical parallel: where those local constraints hold tightly, you should see few avoidable losses (high Carnot efficiency); where they fail, you should find loss hotspots (rework, backtracking, waste heat). The local inconsistencies you describe might correspond directly to local inefficiencies, regions of high irreversibility.
Is there an anthropic reason or computational (solomonoff-pilled) argument for why we would expect to the computational/causal graph of the universe to be this local (sparse)? Or at least appear local to a first approximation. (Bells-inequality)
This seems like a quite special property: I suspect that ether
it is not as rare in e.g. the solomonoff prior as we might first intuit, or
we should expect this for anthropic resons e.g. it is really hard to develop intelligence/do precidctions in nonlocal universes.
In evolution we can tell a story that not only are genes selected for their function, but also for how easily modifiable they are. For example, having a generic antibiotic gene is much more useful than having an antibiotic locked into one target and far, in edit-distance terms, from any other useful variant.
Why would we expect the generic gene to be more common? There is selection pressure on having modifiable genes because environments are constantly shifting (the Red Queen hypothesis). Genes are modules with evolvability baked in by past selection.
Can we make a similar argument for circuits/features/modes in NNs? Obviously it is better to have a more general circuit, but can we also argue that “multitool circuits” are not only better at generalising but also more likely to be found?
SGD does not optimise loss but rather something like free energy, taking degeneracy (multiplicity) into account with some effective temperature.
But evolvability seems distinct from degeneracy. Degeneracy is a property of a single loss landscape, while evolvability is a claim about distribution shift. And the claim is not “I have low loss in the new distribution” but rather “I am very close to a low-loss solution of the new distribution.”
Degeneracy in ML ≈ mutational robustness in biology, which is straightforward, but that is not what I am pointing at here. Evolvability is closer to out-of-distribution adaptivity: the ability to move quickly into a new optimum with small changes.
Are there experiments where a model is trained on a shifting distribution?
Is the shifting distribution relevant or can this just as well be modeled as a mixture of the distributions, and what we think of as OOD is actually in the mixture distribution? In that case degeneracy is all you need.
Related ideas: cryptographic one-way functions (examples of unevolvable designs), out-of-distribution generalisation, mode connectivity.
Excellent! Great to have a cleanly formulated article to point people to!
Good point! My intuition was that the Berkenstein bound (https://en.wikipedia.org/wiki/Bekenstein_bound) limits the amount of information in a volume. (Or more precisely the information surrounded by an area.) Therefore the number of states in a finite volume is also finite.
I must add: since writing this comment, a man called george pointed out to me that, when modeling the universe as a computation one must take care, to not accidentally derive ontological claims from it.
So today I would have a more ‘whatever-works-works’-attitude; UTMs, DFAs both just models, neither likely to be ontologically true.
Wow, thank you for the kind and thorough reply! Obviously there is much more to this, I’ll have a look at the report
I first heard this idea from Joscha Bach, and it is my favorite explanation of free will. I have not heard it called as a ‘predictive-generative gap’ before though, which is very well formulated imo
Really excited to see where this goes!