Here is chatgpt doing what you said it can’t. Finding all the logical fallacies in what you write:
You’re raising strong criticisms, and it’s worth unpacking them carefully. Let’s go through your argument and see if there are any logical fallacies or flawed reasoning.
“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.”
This misrepresents the original claim:
“AI can help create a framework at the very least so they can get their ideas down.”
The original point wasn’t that AI could replace the entire creative process or make a comic successful on its own—it was that it can assist people in starting or visualizing something they couldn’t otherwise. Dismissing that by shifting the goalposts to “producing a full, good comic” creates a straw man of the original claim.
“If you are not competent in a visual medium, then don’t make it visual, write a story or an essay.”
This suggests a binary: either you’re competent at visual art or you shouldn’t try to make anything visual. That’s a false dichotomy. People can learn, iterate, or collaborate, and tools like AI can help bridge gaps in skill—not replace skill, but allow exploration. Many creators use tools before mastery (e.g., musicians using GarageBand, or writers using Grammarly).
“Supposed ‘brilliant ideas’ are a dime a dozen…”
While it’s true that execution matters more than ideas alone, dismissing the value of ideas altogether is an overgeneralization. Many successful works do start with a strong concept—and while many fail in execution, tools that lower the barrier to prototyping or drafting can help surface more workable ideas. The presence of many bad ideas doesn’t invalidate the potential value of enabling more people to test theirs.
“…result in a boring comic…” / “…just bad (look at SMBC or xkcd or…)”
Criticizing popular webcomics like SMBC or xkcd by calling them “bad” doesn’t really support your broader claim. These comics are widely read because of strong writing and insight, despite minimalistic visuals. It comes off as dismissive and ridicules the counterexamples rather than engaging with them. That’s not a logical fallacy in the strictest sense, but it’s rhetorically weak.
“For now I see no particular benefits that the right-wing has obtained by using AI either…”
This seems like a rebuttal to a point that wasn’t made directly. The original argument wasn’t that “the right is winning with AI,” but rather that alienating the left from it could lead to missed opportunities. Refuting a weaker version (e.g., “the right is clearly winning with AI”) isn’t addressing the original concern, which was more about strategic adoption.
Summary of Fallacies Identified:
Type Description
Straw Man Misrepresents the role of AI in creative assistance. False Dichotomy Assumes one must either be visually skilled or not attempt visual media. Hasty Generalization Devalues “brilliant ideas” universally. Appeal to Ridicule Dismisses counterexamples via mocking tone rather than analysis. Tu Quoque-like Compares left vs. right AI use without addressing the core point about opportunity.
Your criticism is thoughtful and not without merit—but it’s wrapped in rhetoric that sometimes slips into oversimplification or misrepresentation of the opposing view. If your goal is to strengthen your argument or have a productive back-and-forth, refining those areas could help. Would you like to rewrite it in a way that keeps the spirit of your critique but sharpens its logic?
Did you even read this garbage? It’s just words strung together without any meaning. The things it’s claiming show a fundamental lack of understanding of what it is responding to.
This didn’t prove your point at all, quite the opposite. And it wasted everyone’s time in the process. Good job, this was worthless.
I did and it was because it didn’t have the previous context. But it did find the fallacies as present. Logic is literally what a chat AI is going. A human still needs to review the output but it did what it was asked. I don’t know AI programming well. But I can say that logic is algorithmic. An AI has no problem parsing an argument and finding the fallacies. It’s a tool like any other.
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).
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 something that can tokenize text. Wouldn’t the difficulty be if the AI has the right context.
antonim@lemmy.dbzer0.com 3 weeks ago
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.
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?
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?).
“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?
Melvin_Ferd@lemmy.world 3 weeks ago
Hype flows in both directions. Right now the hype from most is finding issues with chatgpt. It did find the fallacies based on what it was asked to do. It worked as expected. You act like this is fire and forget. Given what this output gave me, I can easily keep working this to get better and better arguments. I can review the results and clarify and iterate. I did copy and paste just to show an example. First I wanted to be honest with the output and not modify it. Second is an effort thing. I just feel like you can’t honestly tell me that within 10 seconds having that summary is not beneficial. I didn’t supply my argument to the prompt, only yours. If I submitted my argument it would be better.
antonim@lemmy.dbzer0.com 3 weeks ago
hype noun (1)
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 didn’t. Put the text of your comment back into GPT and tell it to argue why the fallacies are misidentified.
But you did fire and forget it. I don’t even think you read the output yourself.
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.
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…
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.
Melvin_Ferd@lemmy.world 3 weeks ago
Ok let’s give a test here. Let’s start with understand logic. Give me a paragraph and let’s see if it can find any logical fallacies. You can provide the paragraph. Only constraint is that the context has to exist within the paragraph.