I had a hilarious exchange on here where I used an LLM to explain to a poster at length why they fundamentally didn't understand what I said. It did a bang up job. The poster, and a lot of other people, got mad I used AI and they still didn't understand my original post, or the AI explanation.
LLMs aren't terribly useful to people who fundamentally can't read. When those people can also type very fast you get the current situation.
> I used an LLM to explain to a poster at length why they fundamentally didn't understand what I said. It did a bang up job. The poster still didn't understand my original post.
It didn't do a bang up job if the poster still didn't understand you, so sorry this example doesn't prove what you think it does.
You have to measure actual results, your own take will always be biased so you can't say "I thought it was great but it didn't work" and expect people to get convinced by that.
Edit: And if that doesn't convince you, why not read what this AI has to say about your post, if you like them so much you should read this right and acknowledge you were wrong just like you expected those people to: https://chatgpt.com/s/t_68f2ae740f98819183539767b921965b
Claude, explain the fallacy fallacy to someone fond of pointing fallacies in arguments:
#### *The Fallacy Fallacy: A Metacognitive Error in Logical Analysis*
The fallacy fallacy, also known as the argument from fallacy or argumentum ad logicam, represents a second-order logical error wherein one incorrectly infers that a conclusion must be false solely because it has been argued through fallacious reasoning. This metacognitive error constitutes a significant impediment to rigorous philosophical discourse and warrants careful examination.
#### *Theoretical Framework and Definition*
Within the domain of informal logic, fallacies constitute "mistakes of reasoning, as opposed to making mistakes that are of a factual nature". The fallacy fallacy emerges when interlocutors conflate the validity of argumentative structure with the truth value of propositional content. Specifically, this error manifests when one advances the following invalid inference pattern:
1. Argument X contains logical fallacy F
2. Therefore, the conclusion C of argument X is false
This inference pattern itself represents a non sequitur, as the presence of fallacious reasoning does not necessarily bear upon the truth or falsity of the conclusion in question.
#### *Epistemological Implications*
The commission of the fallacy fallacy reveals a fundamental misunderstanding of the relationship between logical validity and factual accuracy. *Truth values of propositions exist independently of the quality of arguments marshaled in their support*. A proposition may be demonstrably true despite being defended through specious reasoning, just as a false proposition may be supported by formally valid argumentation with false premises.
Consider the following syllogistic example:
- Major premise: All mammals are warm-blooded
- Minor premise: Dogs are mammals because they bark
- Conclusion: Dogs are warm-blooded
While the minor premise employs irrelevant reasoning (dogs' classification as mammals is unrelated to their vocalization), the conclusion remains factually correct.
#### *Methodological Considerations for Critical Analysis*
Scholars engaged in the identification of logical fallacies must exercise epistemic humility regarding the scope of their critique. As noted in the academic literature, "fallacies are common errors in reasoning that will undermine the logic of your argument", yet this undermining pertains exclusively to the argumentative structure rather than to the ontological status of the conclusion.
The appropriate scholarly response to encountering fallacious reasoning involves:
1. *Methodological separation* - Distinguishing between the evaluation of argumentative form and the assessment of propositional content
2. *Constructive engagement* - Requesting alternative justification rather than dismissing conclusions outright
3. *Epistemic charity* - Acknowledging that interlocutors may possess valid intuitions despite articulating them through flawed logical frameworks
#### *Conclusion*
The fallacy fallacy represents a particularly insidious form of intellectual error, as it masquerades as sophisticated logical analysis while itself committing a fundamental category mistake. Academics and scholars must remain vigilant against this metacognitive trap, recognizing that the identification of fallacious reasoning, while valuable for improving argumentative rigor, does not constitute sufficient grounds for rejecting the truth claims embedded within poorly constructed arguments. The pursuit of truth demands that we evaluate propositions on their merits, independent of the quality of their initial presentation.
See the problem you encounter is that rather than simply saying “just because there was a fallacy in my argument it doesn’t make it false”, you pasted this long, barely digestible, block of text.
In the other conversation “you” “explain“ why other people are misunderstanding you, rather than try to make the argument clearer. Unfortunately the flagged post is no longer available but I’m curious of how such a simple conversation spiraled down so badly.
I even tend to agree with your initial argument so I’m quite convinced that none of this was necessary.
LLMs aren't terribly useful to people who fundamentally can't read. When those people can also type very fast you get the current situation.