And again in a year or so only a handful of tech nerds with few social connections will actually ditch it.

This may be a bit too far outside the nominal topic of the comm, so feel free to report it and let the mods decide if it can stay up. (I’d report it myself but apparently can’t do it.)

The GIF in the OP is from the game Lemmings (1991).

you know what I’m talking about

But I literally don’t. Well, I didn’t but now I mostly do, since you explained it.

I get what you’re saying with regards to the isolation, this issue has already been raised when many left-wing people started to leave Twitter. But it is opening a whole new can of worms - these profiles that post AI-generated content are largely not managed by ordinary people with their private agendas (sharing neat stuff, political agitation, etc.), but by bots, and are also massively followed and supported by other bot profiles. Much the same on Twitter with its hordes of right-wing troll profiles, and as I’m still somewhat active on reddit I also notice blatant manipluation there as well (my country had elections a few weeks ago and the flood of new profiles less than one week old spamming idiotic propaganda and insults was too obvious). It’s not organic online behaviour and it can’t really be fought by organic behaviour, especially when the big social media platforms give up the tools to fight it (relaxing their moderation standards, removing fact-checking, etc.). Lemmy and Mastodon etc. are based on the idea(l) that this corporate-controlled area is not the only space where meaningful activity can happen.

So that’s one side of the story, AI is not something happening in a vacuum and that you just have to submit to your own will. The other side of the story, the actual abilities of AI, have already been discussed, we’ve seen sufficiently that it’s not that good at helping people form more solidly developed and truth-based stances. Maybe it could be used to spread the sort of mass-produced manipulative bullshit that is already used by the right, but I can’t honestly support such stuff. In this regard, we can doubt whether there is any ground to win for the left (would the left’s possible audience actually eat it up), and if yes, whether it is worth it (basing your political appeal on bullshit can bite you in the ass down the line).

As for the comparison to discourse around immigrants, again I still don’t fully understand the point other than on the most surface level (the media is guiding people what to think, duh).

I don’t have even the slightest idea what that video is supposed to mean. (Happy cake day tho.)

In 2005 the article on William Shakespeare contained references to a total of 7 different sources, including a page describing how his name is pronounced, Plutarch, and “Catholic Encyclopedia on CD-ROM”. It contained more text discussing Shakespeare’s supposed Catholicism than his actual plays, which were described only in the most generic terms possible. I’m not noticing any grave mistakes while skimming the text, but it really couldn’t pass for a reliable source or a traditionally solid encyclopedia. And that’s the page on the best known English writer, slightly less popular topics were obviously much shoddier.

It had its significant upsides already back then, sure, no doubt about that. But the teachers’ skepticism wasn’t all that unwarranted.

I think the academic advice about Wikipedia was sadly mistaken.

It wasn’t mistaken 10 or especially 15 years ago, however. Check how some articles looked back then, you’ll see vastly fewer sources and overall a less professional-looking text. These days I think most professors will agree that it’s fine as a starting point (depending on the subject, at least; I still come across unsourced nonsensical crap here and there, slowly correcting it myself).

I think that’s not possible. Wikipedia collects as little user data as possible, and providing a different UX in different countries sounds like it would already be too intrusive in that regard.

As far as I’ve seen they only generated one example summary, which is linked in OP. It’s not good, as Wikipedians have pointed out: https://en.wikipedia.org/wiki/Wikipedia:Village_pump_(technical)#The_Dopamine_summary

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?

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?

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.

That was a roundabout way of admitting you have no idea what logic is or how LLMs work. Logic works with propositions regardless of their literal meaning, LLMs operate with textual tokens irrespective of their formal logical relations. The chatbot doesn’t actually do the logical operations behind the scenes, it only produces the text output that looks like the operations were done (because it was trained on a lot of existing text that reflects logical operations in its content).

Right now the hype from most is finding issues with chatgpt

hype noun (1)

publicity

especially : promotional publicity of an extravagant or contrived kind

You’re abusing the meaning of “hype” in order to make the two sides appear the same, because you do understand that “hype” really describes the pro-AI discourse much better.

It did find the fallacies based on what it was asked to do.

It didn’t. Put the text of your comment back into GPT and tell it to argue why the fallacies are misidentified.

You act like this is fire and forget.

But you did fire and forget it. I don’t even think you read the output yourself.

First I wanted to be honest with the output and not modify it.

Or maybe you were just lazy?

Personally I’m starting to find these copy-pasted AI responses to be insulting. It has the “let me Google that for you” sort of smugness around it. I can put in the text in ChatGPT myself and get the same shitty output, you know. If you can’t be bothered to improve it, then there’s absolutely no point in pasting it.

Given what this output gave me, I can easily keep working this to get better and better arguments.

That doesn’t sound terribly efficient. Polishing a turd, as they say. These great successes of AI are never actually visible or demonstrated, they’re always put off - the tech isn’t quite there yet, but it’s just around the corner, just you wait, just one more round of asking the AI to elaborate, just one more round of polishing the turd, just a bit more faith on the unbelievers’ part…

I just feel like you can’t honestly tell me that within 10 seconds having that summary is not beneficial.

Oh sure I can tell you that, assuming that your argumentative goals are remotely honest and you’re not just posting stupid AI-generated criticism to waste my time. You didn’t even notice one banal way in which AI misinterpreted my comment (I didn’t say SMBC is bad), and you’d probably just accept that misreading in your own supposed rewrite of the text. Misleading summaries that you have to spend additional time and effort double checking for these subtle or not so subtle failures are NOT beneficial.

Excellent, these “fallacies” are exactly as I expected - made up, misunderstanding my comment (I did not call SMBC “bad”), and overall just trying to look like criticism instead of being one. Completely worthless - but I sure can see why right wingers are embracing it!

It’s funny how you think AI will help refine people’s ideas, but you actually just delegated your thinking to it and let it do it worse than you could (if you cared). That’s why I don’t feel like getting any deeper into explaining why the AI response is garbage, I could just as well fire up GPT on my own and paste its answer, but it would be equally meaningless and useless as yours.

Saying it’ll be boring comics missed the entire point.

So what was the point exactly? I re-read that part of your comment and you’re talking about “strong ideas”, whatever that’s supposed to be without any actual context?

Saying it is the same as google is pure ignorance of what it can do.

I did not say it’s the same as Google, in fact I said it’s worse than Google because it can add a hallucinated summary or reinterpretation of the source. I’ve tested a solid number of LLMs over time, I’ve seen what they produce. You can either provide examples that show that they do not hallucinate, that they have access to sources that are more reliable than what shows up on Google, or you can again avoid any specific examples, just expecting people to submit to the revolutionary tech without any questions, accuse me of complete ignorance and, no less, compare me with anti-immigrant crowds (I honestly have no idea what’s supposed to be similar between these two viewpoints? I don’t live in a country with particularly developed anti-immigrant stances so maybe I’m missing something here?).

The people who buy into it will get into these type of ignorant and short sighted statements just to prove things that just are not true. But they’ve bought into the hype and need to justify it.

“They’ve bought into the hype and need to justify it”? Are you sure you’re talking about the anti-AI crowd here? Because that’s exactly how one would describe a lot of the pro-AI discourse. Like, many pro-AI people literally BUY into the hype by buying access to better AI models or invest in AI companies, the very real hype is stoked by these highly valued companies and some of the richest people in the world, and the hype leads the stock market and the objectively massive investments into this field.

But actually those who “buy into the hype” are the average people who just don’t want to use this tech? Huh? What does that have to do with the concept of “hype”? Do you think hype is simply any trend that doesn’t agree with your viewpoints?

I have no idea what sort of AI you’ve used that could do any of this stuff you’ve listed. A program that doesn’t reason won’t expose logical fallacies with any rigour or refine anyone’s ideas. It will link to credible research that you could already find on Google but will also add some hallucinations to the summary. And so on, it’s completely divorced from how the stuff as it is currently works.

Someone with a brilliant comic concept but no drawing ability? AI can help build a framework to bring it to life.

That’s a misguided view of how art is created. Supposed “brilliant ideas” are dime a dozen, it takes brilliant writers and artists to make them real. Someone with no understanding of how good art works just having an image generator produce the images will result in a boring comic no matter the initial concept. If you are not competent in a visual medium, then don’t make it visual, write a story or an essay.

Besides, most of the popular and widely shared webcomics out there are visually extremely simple or just bad (look at SMBC or xkcd or - for a right-wing example - Stonetoss).

For now I see no particular benefits that the right-wing has obtained by using AI either. They either make it feed back into their delusions, or they whine about the evil leftists censoring the models (by e.g. blocking its usage of slurs).

Wow, I would deeply apologise on the behalf of all of us uneducated proles having opinions on stuff that we’re bombarded with daily through the media.

That depends on your assumption that the left would have anything relevant to gain by embracing AI (whatever that’s actually supposed to mean).

But 90% of “reasoning humans” would answer just the same. Your questions are based on some non-trivial knowledge of physics, chemistry and medicine that most people do not possess.

As I said in an another comment, I find that traditional encyclopedias fare better than Wikipedia in this respect. Wikipedians can muddle even comparatively simple topics, e.g. linguistic purism is described like this:

Linguistic purism or linguistic protectionism is a concept with two common meanings: one with respect to foreign languages and the other with respect to the internal variants of a language (dialects). The first meaning is the historical trend of the users of a language desiring to conserve intact the language’s lexical structure of word families, in opposition to foreign influence which are considered ‘impure’. The second meaning is the prescriptive[1] practice of determining and recognizing one linguistic variety (dialect) as being purer or of intrinsically higher quality than other related varieties.

This is so hopelessly awkward, confusing and inconsistent. (I hope I’ll get around to fixing it, btw.) Compare it with how the linguist RL Trask defines it in his Language and Linguistics: The Key Concepts:

[Purism] The belief that words (and other linguistic features) of foreign origin are a kind of contamination sullying the purity of a language.

Bam! No LLMs were needed for this definition.

So here’s my explanation for this problem: Wikipedians, specialist or non-specialist, like to collect and pile up a lot of cool info they’ve found in literature and online. When you have several such people working simultaneously, you easily end up with chaotic texts with no head or tails, which can always be expanded further and further with new stuff you’ve found because it’s just a webpage with no technical limits. When scholars write traditional encyclopedic texts, the limited space and singular viewpoint force them to write something much more coherent and readable.

Yeah, the catastrophic comments do take it too far… WMF has already announced they’re putting it on hold, so at the very least there’s a lot of discussion with the editors and additional work that will have to happen before this launches - if it ever launches.