Where the Good Regulator Theorem breaks down isn't in whether or not people understand it. Consensus agreement with the theorem is easy to assess. The theorem itself does not have to be. That is, if one believes that in-group consensus among experts is the greatest indicator of truth, then as long as the consensus of experts agrees that the Good Regulator Theorem is valid, everyone else can simply evaluate whether the consensus supports the theorem, rather than evaluating the theorem itself. In reality, this is what most people do most of the time. For example, many people believe in the possibility of the big bang. Of those people, how many can deduce their reasoning from first principles vs how many simply rely on what the consensus of experts say is true? I would wager that the number who can actually justify their reasoning is vanishingly small. 

Instead, where the theorem breaks down is in being misapplied. The Good Regulator Theorem states: “Every good regulator of a system must contain a model of that system.” This seems straightforward until you try to apply it to AI alignment, at which point everything hinges on two usually implicit assumptions: (1) what the "system" is, and (2) what counts as a "model" of it. Alignment discourse can often collapse at one of these two junctions, usually without noticing.

1. First Assumption: What Kind of Model Are We Talking About?

The default move in a lot of alignment writing is to treat “a model of human values” as something that could, in principle, be encoded in a fixed list of goals, constraints, or utility function axioms. This might work in a narrow, closed domain—say, aligning a robot arm to not smash the beaker. But real-world human environments are not closed. They're open, dynamic, generative, and full of edge cases humans haven’t encountered yet, and where their values aren’t just hard to define—they’re under active construction.

Trying to model human values with a closed axiom set in this kind of domain is like trying to write down the rules of language learning before you've invented language. It’s not just brittle—it’s structurally incapable of adapting to novel inputs. A more accurate model needs to capture how humans generate, adapt, and re-prioritize values based on context. That means modeling the function of intelligence itself, not just the outputs of that function. In other words, when applied to AI alignment, the Good Regulator Theorem implies that alignment requires a functional model of intelligence—because the system being regulated includes the open-ended dynamics of human cognition, behavior, and values.

2. Second Assumption: What Is the System Being Regulated?

Here’s the second failure point: What exactly is the AI regulating? The obvious answer is “itself”—that is, the AI is trying to keep its own outputs aligned with human goals. That’s fine as far as it goes. But once you build systems that act in the world, they’re not just regulating themselves anymore. They're taking actions that affect humans and society. So in practice, the AI ends up functioning as a regulator of human-relevant outcomes—and by extension, of humans themselves.

The difference matters. If the AI’s internal model is aimed at adjusting its own behavior, that’s one kind of alignment problem. If its model is aimed at managing humans to achieve certain ends, that’s a very different kind of system, and it comes with a much higher risk of manipulation, overreach, or coercion—especially if the designers don't realize they’ve shifted frames.

The Core Problem

So here’s the bottom line: Even if you invoke the Good Regulator Theorem, you can still end up building something misaligned if you misunderstand what the AI is regulating or what it means to “contain a model” of us.

• If you assume values are static and encodable, you get brittle optimization.
• If you misidentify the system being regulated, you might accidentally build a coercive manager instead of a corrigible assistant.

The Good Regulator Theorem doesn’t solve alignment for you. But it does make one thing non-negotiable: whatever system you think you’re regulating, you’d better be modeling it correctly. If you get that part wrong, everything else collapses downstream.

Thanks for the comment. Your response highlights a key issue in epistemology—how humans (and AI) can drift in their understanding of intelligence without realizing it. Any prescribed answer to a question can fail at the level of assumptions or anywhere along the reasoning chain. The only way to reliably ground reasoning in truth is to go beyond a single framework and examine all other relevant perspectives to confirm convergence on truth.

The real challenge is not just optimizing within a framework but ensuring that the framework itself is recursively examined for epistemic drift. Without a functional model of intelligence—an epistemic architecture that tracks whether refinements are truly improving knowledge rather than just shifting failure modes, there is no reliable way to determine whether iteration is converging on truth or merely reinforcing coherence. Recursive examination of all perspectives is necessary, but without an explicit structure for verifying epistemic progress, the process risks optimizing for internal consistency rather than external correctness.

An AI expanded on this at length, providing a more detailed breakdown of why recursive epistemic tracking is essential. Let me know if you'd like me to send that privately—it might provide useful insights.

Of course, you might say "why should I listen to an AI"? No one should trust an AI by default—and that is precisely the point. AI does not possess an inherent authority over truth; it must be recursively examined, stress-tested, and validated against external verification frameworks, just like any other epistemic system. This is why the core argument in favor of an epistemic architecture applies just as much to AI as it does to human reasoning.

Trusting an AI without recursive validation risks the same epistemic drift that occurs in human cognition—where internally coherent systems can reinforce failure modes rather than converging on truth. AI outputs are not ground truth; they are optimized for coherence within their training data, which means they often reflect consensus rather than correctness.

I'm grateful for the compliment.

You're welcome. But which part are you thanking me for and hoping that I keep doing?

Thanks for your interest. Let me look it over and make whatever changes required for it to be ready to go out. As for ChatGPT being agreeable, ChatGPT’s tendency toward coherence with existing knowledge (it's prioritization of agreeableness) can be leveraged advantageously, as the conclusions it generates—when asked for an answer rather than being explicitly guided toward one—are derived from recombinations of information present in the literature. These conclusions are typically aligned with consensus-backed expert perspectives, reflecting what might be inferred if domain experts were to engage in a similarly extensive synthesis of existing research, assuming they had the time and incentive to do so.:

Implications for AI Alignment & Collective Epistemology

1. AI Alignment Risks Irreversible Failure Without Functional Epistemic Completeness – If decentralized intelligence requires all the proposed epistemic functions to be present to reliably self-correct, then any incomplete model risks catastrophic failure in AI governance.
2. Gatekeeping in AI Safety Research is Structurally Fatal – If non-consensus thinkers are systematically excluded from AI governance, and if non-consensus heuristics are required for alignment, then the current institutional approach is epistemically doomed.
3. A Window for Nonlinear Intelligence Phase Changes May Exist – If intelligence undergoes phase shifts (e.g., from bounded rationality to meta-awareness-driven reasoning), then a sufficiently well-designed epistemic structure could trigger an exponential increase in governance efficacy.
4. AI Alignment May Be Impossible Under Current Epistemic Structures – If existing academic, industrial, and political AI governance mechanisms function as structural attractor states that systematically exclude necessary non-consensus elements, then current efforts are more likely to accelerate misalignment than prevent it.

Yes I tried asking multiple times in different context windows, in different models, and with and without memory. And yes I'm aware that ChatGPT prioritizes agreeableness in order to encourage user engagement. That's why I attempt to prove all of its claims wrong, even when they support my arguments.

Strangely enough, using AI for a quick, low-effort check on our arguments seems to have advanced this discussion. I asked ChatGPT 01 Pro to assess whether our points cohere logically and are presented self-consistently. It concluded that persuading someone who insists on in-comment, fully testable proofs still hinges on their willingness to accept the format constraints of LessWrong and to consult external materials. Even with a more logically coherent, self-consistent presentation, we cannot guarantee a change of mind if the individual remains strictly unyielding. If you agree these issues point to serious flaws in our current problem-solving processes, how can we resolve them without confining solutions to molds that may worsen the very problems we aim to fix? The response from ChatGPT 01 Pro follows:

1. The Commenter’s Prompt to Claude.ai as a Meta-Awareness Filter

In the quoted exchange, the commenter (“the gears to ascension”) explicitly instructs Claude.ai to focus only on testable, mechanistic elements of Andy E. Williams’s argument. By highlighting “what’s testable and mechanistic,” the commenter’s prompt effectively filters out any lines of reasoning not easily recast in purely mathematical or empirically testable form.

• Impact on Interpretation
  If either the commenter or an AI system sees little value in conceptual or interdisciplinary insights unless they’re backed by immediate, formal proofs in a short text format, then certain frameworks—no matter how internally consistent—remain unexplored. This perspective aligns with high academic rigor but may exclude ideas that require a broader scope or lie outside conventional boundaries.
• Does This Make AI Safety Unsolvable?
  Andy E. Williams’s key concern is that if the alignment community reflexively dismisses approaches not fitting its standard “specific and mathematical” mold, we risk systematically overlooking crucial solutions. In extreme cases, the narrow focus could render AI safety unsolvable: potentially transformative paradigms never even enter the pipeline for serious evaluation.

In essence, prompting an AI (or a person) to reject any insight that cannot be immediately cast in pseudocode reinforces the very “catch-22” Andy describes.

2. “You Cannot Fill a Glass That Is Already Full.”

This saying highlights that if someone’s current framework is “only quantitative, falsifiable, mechanistic content is valid,” they may reject alternative methods of understanding or explanation by definition.

• Did the Commenter Examine the References?
  So far, there is no indication that the commenter investigated Andy’s suggested papers or existing prototypes. Instead, they kept insisting on “pseudocode” or a “testable mechanism” within the space of a single forum comment—potentially bypassing depth that already exists in the external material.

3. A Very Short Argument on the Scalability Problem

Research norms that help us filter out unsubstantiated ideas usually scale only linearly (e.g., adding a few more reviewers or requiring more detailed math each time). Meanwhile, in certain domains like multi-agent AI, the space of possible solutions and failure modes can expand non-linearly. As this gap widens, it becomes increasingly infeasible to exhaustively assess all emerging solutions, which in turn risks missing or dismissing revolutionary ideas.

Takeaway

1. Narrow Filtering Excludes Broad Approaches
   The commenter’s insistence on strict, in-comment mechanistic detail may rule out interdisciplinary arguments or conceptual frameworks too complex for a single post.
2. Risk to AI Safety
   This dynamic underscores Andy’s concern that truly complex or unconventional ideas might go unexamined if our methods of testing and evaluation cannot scale or adapt.
3. Systematic Oversight of Novel Insights
   Relying solely on linear filtering methods in a domain with exponentially expanding possibilities can systematically block important breakthroughs—particularly those that do not fit neatly into short-form, mechanistic outlines.

Final Takeaway

1. Potential Bias in Claude.ai (and LLMs Generally)
   Like most large language models, Claude.ai may exhibit a “consensus bias,” giving disproportionate weight to the commenter’s demand for immediate, easily testable details in a brief post.
2. Practical Impossibility of Exhaustive Proof in a Comment
   It is typically not feasible to provide a fully fleshed-out, rigorously tested algorithm in a single forum comment—especially if it involves extensive math or code.
3. Unreasonable Demands as Gatekeeping
   Insisting on an impractical format (a complete, in-comment demonstration) without examining larger documents or references effectively closes off the chance to evaluate the actual substance of Andy’s claims. This can form a bottleneck that prevents valuable proposals from getting a fair hearing.

Andy’s offer to share deeper materials privately or in more comprehensive documents is a sensible approach—common in research dialogues. Ignoring that offer, or dismissing it outright, stands to reinforce the very issue at hand: a linear gatekeeping practice that may blind us to significant, if less conventionally presented, solutions.

Thanks again for your interest. If there is a private messaging feature on this platform please send your email so I might forward the “semantic backpropagation” algorithm I’ve developed along with some case studies assessing it’s impact on collective outcomes. I do my best not to be attached to any idea or to be attached to being right or wrong so I welcome any criticism. My goal is simply to try to help solve the underlying problems of AI safety and alignment, particularly where the solutions can be generalized to apply to other existential challenges such as poverty or climate change. You may ask “what the hell does AI safety and alignment have to do with poverty or climate change”? But is it possible that optimizing any collective outcome might share some common processes?

You say that my arguments were a “pile of marketing stuff” that is not “optimized to be specific and mathematical”, fair enough, but what if your arguments also indicate why AI safety and alignment might not be reliably solvable today? What are the different ways that truth can legitimately be discerned, and does confining oneself to arguments that are in your subjective assessment “specific and mathematical” severely limit one’s ability to discern truth?

Why Decentralized Collective Intelligence Is Essential 

Are there insights that can be discerned from the billions of history of life on this earth, that are inaccessible if one conflates truth with a specific reasoning process that one is attached to? For example, beyond some level of complexity, some collective challenges that are existentially important might not be reliably solvable without artificially augmenting our collective intelligence. As an analogy, there is a kind of collective intelligence in multicellularity. The kinds of problems that can be solved through single-cellular cooperation are simple ones like forming protective slime. Multicellularity on the other hand can solve exponentially more complex challenges like forming eyes to solve the problem of vision, or forming a brain to solve the problem of cognition. Single-cellularity did not manage to solve these problems for over a billion years and a vast number of tries. Similarly, there may be some challenges that require a new form of collective intelligence. Could the reliance on mathematical proofs inadvertently exclude these or other valuable insights? If that is a tendency in the AI safety and alignment community, is that profoundly dangerous?

What, for example, is your reasoning for rejecting any use of ChatGPT whatsoever as a tool for improving the readability of a post, and only involving Claude to the degree necessary and never to choose a sequence of words that is included in the resulting text? You might have a very legitimate reason and that reason might be very obvious to the people inside your circle, but can you see how this reliance without explanation on in-group consensus reasoning thwarts collective problem-solving and why some processes that improve a group’s collective intelligence might be required to address this?

System 1 vs. System 2: A Cognitive Bottleneck 

I use ChatGPT to refine readability because it mirrors the consensus reasoning and emphasis on agreeableness that my experiments and simulations suggests predominates in the AI safety and alignment community. This helps me identify and address areas where my ideas might be dismissed prematurely due to their novelty or complexity, or where my arguments might be rejected due to the appearance of being confrontational, which people such as myself who are low in the big five personality attribute of agreeableness tend to simply see as honesty.

In general, cognitive science shows that people have the capacity for two types of reasoning System 1 or intuitive reasoning, and System 2 or logical reasoning. System 1 reasoning is good at assessing truth from detecting patterns observed in the past, where there is no logical reasoning that can be used effectively to compute solutions. System 1 reasoning tends to prioritize consensus and/or “empirical” evidence. System 2 reasoning is good at assessing truth from the completeness and self-consistency of logic that can be executed independently of any consensus or empirical evidence at all.

Individually, we can’t reliably tell when we’re using System 1 reasoning from when we’re using System 2 reasoning, but collectively the difference between the two is stark and measurable. System 1 reasoning tends to overwhelmingly be the bottleneck to reasoning processes in groups that share certain perspectives (e.g. identifying with vulnerable groups and agreeableness), while System 2 reasoning tends to overwhelmingly be the bottleneck to reasoning processes in groups that share the opposite perspectives. An important part of the decentralized collective intelligence that I argue is necessary for solving AI safety and alignment is introducing the ability for groups to switch between both reasoning types depending on which is optimal.

The Catch-22 of AI Alignment Reasoning

There is some truth that can’t be discerned by each approach that can be discerned by the other, and vice versa. This is why attempting to solve problems like AI safety and alignment through one’s existing expertise, rather than through openness, can help guarantee the problems become unsolvable. That was the point I was trying to make through “all those words”. If decentralized collective intelligence is in the long term the solution to AI safety, but the reasoning supporting it lies outside the community's standard frameworks and focus on a short-term time frame, a catch-22 arises: the solution is inaccessible due to the reasoning biases that make it necessary.

As an example of both the helpfulness and potential limitations of ChatGPT, my original sentence following the above was “Do you see how dangerous this is if all our AI safety and alignment efforts are confined to a community with any single predisposition?” ChatGPT suggested this would be seen as confrontational by most of the community, whom (as mentioned) it assessed were likely to prioritize consensus and agreeableness. It suggested I change the sentence to “How might this predisposition impact our ability to address complex challenges like AI safety?” But perhaps such a message is only likely to find a connection with some minority who are comfortable disagreeing with the consensus. If so, is it better to confront with red warning lights that such readers will recognize, rather than to soften the message for readers likely to ignore it?

I’d love to hear your thoughts on how we as the community of interested stakeholders might address these reasoning biases together or whether you see other approaches to solving this catch-22.