This is why I said I wasn’t sure how AI works behind the scenes. But I do know that logic isn’t difficult. Just to not fuck around between us. I have a CS background. Only saying this because I think you may have it as well and we can save some time.
It makes sense to me that logic is something AI can parse easily. Logic in my mind is very easy if it can tokenize some text. Wouldn’t the difficulty be if the AI has the right context.
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”).
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:
Fallacy
Example from Text
Explanation
Hasty Generalization
“Almost all men… cherish very nearly the same feelings…”
Overgeneralizes personal feeling
False Cause
“…driving off the spleen and regulating the circulation.”
Implies unproven health benefits
Appeal to Emotion
“…prevent me from… knocking people’s hats off.”
Justifies behavior with emotion
False Analogy
“Cato throws himself… I quietly take to the ship.”
Equates suicide and sailing
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
Fallacy Type
Description
Hasty Generalization
Rejects all sensory data due to occasional errors.
False Analogy
Compares unreliable senses to untrustworthy people.
Slippery Slope
Claims that doubting foundations causes collapse of all beliefs.
Begging the Question
Uses reason to justify doubting everything, including reason itself.
Inconsistency / Special Pleading
Makes an exception for immediate sensory beliefs without justification.
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?
This is why I said I wasn’t sure how AI works behind the scenes. But I do know that logic isn’t difficult. Just to not fuck around between us. I have a CS background. Only saying this because I think you may have it as well and we can save some time.
It makes sense to me that logic is something AI can parse easily. Logic in my mind is very easy if it can tokenize some text. Wouldn’t the difficulty be if the AI has the right context.
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
2. False Cause (Post Hoc)
3. Appeal to Emotion
4. False Analogy
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
2. False Analogy
3. Slippery Slope (Metaphorical)
4. Begging the Question (Circular Reasoning)
5. Inconsistency (Recognized, Not Fully Resolved)
✅ Summary Table of Fallacies
Conclusion:
Descartes’ passage is methodologically rich, but from a logic and reasoning perspective, it contains:
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?