Well - if you want to devolve into argument, you can argue all day long about "what is reasoning?"

I agree with you. In its current state, LLM is not sentient, and thus not "Intelligence".

You're correct that the formal definition of a Markov process does not exclude internal computation, and that it only requires the next state to depend solely on the current state. But what defines a classical Markov chain in practice is not just the formal dependency structure but how the transition function is structured and used. A traditional Markov chain has a discrete and enumerable state space with explicit, often simple transition probabilities between those states. LLMs do not operate this way.

The claim that an LLM is "just" a large compressed Markov chain assumes that its function is equivalent to a giant mapping of input sequences to output distributions. But this interpretation fails to account for the fundamental difference in how those distributions are generated. An LLM is not indexing a symbolic structure. It is computing results using recursive transformations across learned embeddings, where those embeddings reflect complex relationships between tokens, concepts, and tasks. That is not reducible to discrete symbolic transitions without losing the model’s generalization capabilities. You could record outputs for every sequence, but the moment you present a sequence that wasn't explicitly in that set, the Markov table breaks. The LLM does not.

Yes, you can say a table is just one implementation of a function, and from a purely mathematical perspective, any function can be implemented as a table given enough space. But the LLM’s function is general-purpose. It extrapolates. A precomputed table cannot do this unless those extrapolations are already baked in, in which case you are no longer talking about a classical Markov system. You are describing a model that encodes relationships far beyond discrete transitions.

The pi analogy applies to deterministic functions with fixed outputs, not to learned probabilistic functions that approximate conditional distributions over language. If you give an LLM a new input, it will return a meaningful distribution even if it has never seen anything like it. That behavior depends on internal structure, not retrieval. Just because a function is deterministic at temperature 0 does not mean it is a transition table. The fact that the same input yields the same output is true for any deterministic function. That does not collapse the distinction between generalization and enumeration.

So while yes, you can implement any deterministic function as a lookup table, the nature of LLMs lies in how they model relationships and extrapolate from partial information. That ability is not captured by any classical Markov model, no matter how large.

And that's pretty damn useful, but obnoxious to have expectations wildly set incorrectly.

Is "model" not defined as architecture+weights? Those models certainly don't share the same architecture. I might just be confused about your point though

People think they want AI, but they don’t even know what AI is on a conceptual level.

We actually have sentience, though, and are capable of creating new things and having realizations. AI isn’t real and LLMs and dispersion models are simply reiterating algorithmic patterns, no LLM or dispersion model can create anything original or expressive.

Also, we aren’t “evolved primates.” We are just primates, the thing is, primates are the most socially and cognitively evolved species on the planet, so that’s not a denigrating sentiment unless your a pompous condescending little shit.

Impressive = / = substantial or beneficial.

And what I mean is that prior to the mid 1900s the etymology didn't exist to cause that confusion of terms. Neither Babbage's machines nor prior adding engines were called computers or calculators. They were 'machines' or 'engines'.

Babbage's machines were novel in that they could do multiple types of operations, but 'mechanical calculators' and counting machines were ~200 years old. Other mathematical tools like the abacus are obviously far older. They were not novel enough to cause confusion in anyone with even passing interest.

But there will always be people who just assume 'magic', and/or "it works like I want it to".

Peak pseudo-science. The burden of evidence is on the grifters who claim "reason". But neither side has any objective definition of what "reason" means. It's pseudo-science against pseudo-science in a fierce battle.

Particularly to counter some more baseless marketing assertions about the nature of the technology.

It's hard to to be heard when you're buried under all that sweet VC/grant money.

Even defining reason is hard and becomes a matter of philosophy more than science. For example, apply the same claims to people. Now I've given you something to think about. Or should I say the Markov chain in your head has a new topic to generate thought states for.

It is, but this did not prove all architectures cannot reason, nor did it prove that all sets of weights cannot reason.

essentially they did not prove the issue is fundamental. And they have a pretty similar architecture, they're all transformers trained in a similar way. I would not say they have different architectures.

Without being explicit with well researched material, then the marketing presentation gets to stand largely unopposed.

So this is good even if most experts in the field consider it an obvious result.

Yeah I often think about this Rick N Morty cartoon. Grifters are like, "We made an AI ankle!!!" And I'm like, "That's not actually something that people with busted ankles want. They just want to walk. No need for a sentient ankle." It's a real gross distortion of science how everything needs to be "AI" nowadays.

Logic requires abstracting the argumentative form from the literal linguistic content and then generalising it, just how like math is done properly when you work with numbers and not just with sentences such as "two apples and three apples is five apples" (such abstraction in practice allows far more powerful and widely applicable operations than dealing with individual linguistic expressions; if you've ever solved very complex truth trees you'll know how they allow streamlining and solutions that would be practically impossible to do if you had only the ordinary linguistic expression of the same problem). Logic doesn't operate with textual tokens but with logical propositions and operators. "Difficulty" is not a meaningful term here, a tool is either technically capable of doing something (more or less successfully) or it isn't.

That LLMs aren't capable of this sort of precision and abstraction is shown by the OP link as well as the simple fact that chatbots used to be extremely bad at math (which is now probably patched up by adding a proper math module, rather than relying on the base LLM - my assumption, at least).

As for trying more examples of looking for logical fallacies, I tried out three different types of text. Since you say context is important, it's best to take only the beginning of a text. One text I tried is the opening of the Wikipedia article on "history", which ChatGPT described like this: "The passage you've provided is an informative and largely neutral overview of the academic discipline of history. It doesn't make any strong arguments or persuasive claims, which are typically where logical fallacies appear." It then went on to nitpick about some details "for the sake of thorough analysis", but basically had no real complaints. Then I tried out the opening paragraph of Moby-Dick. That's a fictional text so it would be reasonable to reject analysing its logical solidity, as GPT already did with the WP article, but it still tried to wring out some "criticism" that occasionally shows how it misunderstands the text (just as it misunderstood a part of my comment above). Finally, I asked it to find the fallacies in the first four paragraphs of Descartes' Meditations on First Philosophy, which resulted in a criticism that was based on less logically rigid principles than the original text (accusing Descartes of the "slippery slope fallacy").

I'll post the full replies below.

This famous passage from the opening of Moby-Dick by Herman Melville is rich in literary style but not necessarily constructed as an argument, which makes identifying formal logical fallacies a nuanced task. That said, we can identify a few rhetorical or informal fallacies—not because the text is poorly reasoned, but because it makes some sweeping or questionable assumptions in a stylistically persuasive way. Here's a breakdown:

1. Hasty Generalization

"Almost all men in their degree, some time or other, cherish very nearly the same feelings towards the ocean with me."

• Fallacy: The narrator generalizes his deeply personal and specific emotional reaction to the sea as something nearly all men experience.
• Why it’s fallacious: No evidence is presented to support this broad claim. It is based purely on the narrator’s subjective experience and intuition.

2. False Cause (Post Hoc)

"It is a way I have of driving off the spleen and regulating the circulation."

• Fallacy: Implies a causal relationship between going to sea and improved physical/emotional health.
• Why it’s fallacious: While sailing may coincidentally improve his mood or circulation, the text offers no medical or psychological basis to prove a direct causal link.

3. Appeal to Emotion

"...especially whenever my hypos get such an upper hand of me, that it requires a strong moral principle to prevent me from deliberately stepping into the street, and methodically knocking people’s hats off..."

• Fallacy: Uses vivid emotional language to justify behavior or state of mind rather than logical reasoning.
• Why it’s fallacious: It appeals to the reader’s empathy or amusement to legitimize the narrator’s melancholy and coping strategy, rather than offering a rational justification.

4. False Analogy

"With a philosophical flourish Cato throws himself upon his sword; I quietly take to the ship."

• Fallacy: Compares going to sea with committing suicide as if they are equivalent responses to despair.
• Why it’s fallacious: The analogy is emotionally compelling, but equating self-harm with a change in setting (boarding a ship) overlooks major differences in motive and consequence.

Summary:

Would you like me to rewrite the passage without the fallacies, or is this for literary analysis?

Thank you! This passage is again drawn from René Descartes' Meditations on First Philosophy, and it outlines his method of radical doubt as a means to establish certainty in knowledge. While the reasoning is carefully crafted and influential in the history of philosophy, it still contains a few logical fallacies or reasoning weaknesses that can be critically assessed.

Identified Logical Fallacies and Weak Reasoning:

1. Hasty Generalization

"Whatever I have accepted until now as most true has come to me through my senses. But occasionally I have found that they have deceived me, and it is unwise to trust completely those who have deceived us even once."

• Why it’s a fallacy: The fact that the senses occasionally deceive (e.g. in illusions, dreams, or misperceptions) does not justify rejecting them entirely.
• Type: Hasty generalization – concluding that because something is sometimes unreliable, it must always be unreliable.

2. False Analogy

"...it is unwise to trust completely those who have deceived us even once."

• Why it’s a fallacy: Comparing senses (which are not agents but biological faculties) to people who deceive is not a valid analogy. People deceive with intent; senses make errors unintentionally.
• Type: False analogy – treating unlike things as if they were meaningfully similar.

3. Slippery Slope (Metaphorical)

"Once the foundations of a building have been undermined, the rest collapses of its own accord..."

• Why it’s a fallacy: This implies that if some foundational beliefs are doubted, then all other beliefs must collapse, without demonstrating that all knowledge is entirely dependent on those foundations.
• Type: Slippery slope – assuming that undermining one part inevitably leads to a total collapse.

4. Begging the Question (Circular Reasoning)

"My reason tells me... I should withhold assent from [beliefs] that are not completely certain and indubitable."

• Why it’s questionable: Descartes is relying on reason to justify doubting everything else, including the faculties (like reason) he has not yet proven to be trustworthy. This risks begging the question, assuming the reliability of reason while attempting to prove everything else, including reason itself.
• Type: Begging the question – assuming what you're trying to prove.

5. Inconsistency (Recognized, Not Fully Resolved)

"Yet although the senses sometimes deceive us... that doesn’t apply to my belief that I am here, sitting by the fire..."

• Why it’s a fallacy: Here, Descartes briefly exempts ordinary sensory experiences (like feeling warmth, seeing paper) from radical doubt—despite having just declared that any doubt justifies withholding belief. He later corrects for this in the next meditation (introducing the dream argument), but within this passage, it’s a moment of inconsistency.
• Type: Special pleading or internal inconsistency.

Summary Table of Fallacies

Conclusion:

Descartes' passage is methodologically rich, but from a logic and reasoning perspective, it contains:

• Several classic fallacies used to motivate extreme skepticism.
• Analogical and metaphorical reasoning that may be rhetorically persuasive but logically flawed.
• Self-referential assumptions that are philosophically problematic (and which he tries to resolve in later meditations).

Would you like a version of this reasoning revised to be more logically sound, or would you like help analyzing the next part of the Meditations?

There's probably alot of misunderstanding because these grifters intentionally use misleading language: AI, reasoning, etc.

If they stuck to scientifically descriptive terms, it would be much more clear and much less sensational.