site banner
PaperclipPerfector  1yr ago (text post)   37122 thread views

Culture War Roundup for the week of April 10, 2023

This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.

Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.

We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:

  • Shaming.

  • Attempting to 'build consensus' or enforce ideological conformity.

  • Making sweeping generalizations to vilify a group you dislike.

  • Recruiting for a cause.

  • Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.

In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:

  • Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.

  • Be as precise and charitable as you can. Don't paraphrase unflatteringly.

  • Don't imply that someone said something they did not say, even if you think it follows from what they said.

  • Write like everyone is reading and you want them to be included in the discussion.

On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.

14
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Ironically, I think the real existential threat posed by GPT is not to humanity but to humanities professors.

Why can the humanities never catch a break?

TheMotte is a humanities discussion forum. We take questions from the humanities (mainly politics and philosophy) and discuss them using methods of analysis that are typical of the humanities. Anyone who posts here shows a revealed preference for humanistic thinking and, plainly, symbol manipulation as well.

What you have written here, in this very post, is a humanities essay. You have engaged in armchair psychological speculation about the motivations and thought processes of a vast and heterogeneous group of people while adducing very little empirical evidence to support your claims. You haven't defined a precise hypothesis (how could we turn "GPT-4 is exposing post-modernism and the entire edifice of contemporary academia as the farce it's always been" into an empirically falsifiable hypothesis?), collected a sufficiently large sample, done a rigorous statistical analysis, or anything else that might move your speculations out of the realm of "mere humanities" and into the vaunted halls of science. This isn't meant to be a criticism of your post, of course. I too prefer to do all my thinking from the armchair - it's a very comfy place to be. We should just recognize it for what it is, is all. You should reflect on whether what you're doing here - what any of us are doing here - is really any different from what the "postmodernist symbol manipulators" are doing.

What you have written here, in this very post, is a humanities essay.

You're absolutely correct.

But my post makes no particular claims about "the humanities" as a field, what it talks about is "humanities professors" which are not the same thing. Though perhaps the conflation of the former with the latter is yet another example of that inferential distance I've been talking about.

see @07mk's reply below.

I think he would not disagree. I ran Hlynka's text through Bing Chat and this was its summary regarding the humanities professor part:

The author is suggesting that GPT-4 and humanities professors have similar goals and methods, and that they are both inferior to thing-manipulators who can challenge their claims with facts and data. He is implying that GPT-4 could replace humanities professors because they are both producing meaningless or misleading content.

I asked about some counterarguments and here is what it came up with:

The author’s distinction between thing-manipulators and symbol-manipulators is too simplistic and ignores the diversity and complexity of both types of activities. Symbols are not just arbitrary or meaningless signs, but tools for communication, reasoning, and representation that can have various interpretations and functions. Symbols can also be manipulated in ways that reflect the properties and relationships of the things they represent, such as in mathematics or computer science. Thing-manipulators are not just concerned with facts and data, but also with creativity, intuition, and problem-solving. Thing-manipulation can also involve symbolic aspects, such as using models, diagrams, or equations to describe or analyze physical phenomena. Both thing-manipulators and symbol-manipulators can benefit from each other’s perspectives and methods, and collaborate to solve hard social problems that require both empirical and conceptual approaches123

I then asked it to tailor an argument in favor of humanities professors. It searched for "value of humanities professors" on google and incorporated it into the context:

Humanities professors are not just producing symbols and feelings that appeal to a certain audience, but engaging with the world in important ways. They are exploring the diversity and complexity of human cultures, values, and experiences, and contributing to the advancement of knowledge, creativity, and critical thinking. They are also addressing the ethical, social, and political challenges that face humanity in the present and the future, and fostering dialogue and understanding among different perspectives and communities. Humanities professors are not disconnected from reality, but rather enriching it with their insights and interpretations12

I then asked it if all those things cannot be also done by GPT-4. It then searched for "GPT-4 limitations and capabilities" and it came up with the following:

It is possible that GPT-4 can perform some of the tasks that humanities professors do, such as writing essays, generating quotes, or passing exams. However, GPT-4 is not a substitute for humanities professors, because it still has many limitations and challenges that prevent it from achieving the same level of understanding, creativity, and ethics as human scholars. For example, GPT-4 has difficulty with:

  • Distinguishing between true and false statements, and between real and imagined scenarios1
  • Reasoning, planning ahead, working memory, and backtracking, due to its autoregressive architecture2
  • Avoiding social biases, hallucinations, and adversarial prompts that can affect its outputs3
  • Handling visual input, which is not yet widely available or reliable4

Therefore, GPT-4 is not likely to replace humanities professors anytime soon, but rather complement their work or provide new opportunities for collaboration and innovation.

So in a way we came full circle, the last part is I think a version of original argument Hlynka made.

So in a way we came full circle, the last part is I think a version of original argument Hlynka made.

Not really no, and to be blunt my initial reaction reading your "exchange" largely mirrors @IGI-111's below, it really does read like student who hasn't read the material trying to bluff-thier way past the teacher.

Volokh's essay and the subsequent discussion on his blog goes into in this far more deeply than I could, but what it seems that GPT and other LLMs seem to be actually kind of good for is condensing large bodies of text into a "cliff notes" version. For example, GPT was able to correctly identify my supposition that "GPT-4 could replace humanities professors because they are both producing meaningless or misleading content" despite my not having explicit made that claim. What GPT/LLMs seem to be particularly bad at is answering questions.

Ah man it really is like talking to an academic bullshitter. Continuum fallacies and all.

It even brings in random definitions of things that have no connection to the underlying argument just to make the aggrieved party sound more important.

All the tactics, none of the substance.

The hopelessly ironic part is that it seems to be arguing that humanities professors can distinguish between true and false and avoid social biases, having been trained on their writings.

One has seldom produced such a clear example of self refuting nature of the post modern condition.

The hopelessly ironic part is that it seems to be arguing that humanities professors can distinguish between true and false and avoid social biases, having been trained on their writings.

It is arguing in favor of humanities professors because I told it to argue that position. It researched that GPT may have trouble discerning true and false statement, and it argued that humanities professors have that capacity. It implicitly asserted that argument, but Hlynka asserts without proof that humanities professors are pomo text generators. But unlike Hlynka GPT it at least provided links to its statements, it used some jargon like autoregressive architecture and in general repeated original Hlynka's argument about deficiencies of GPT better. I think that it also correctly pointed out that this whole thing vs symbol manipulator distinction is a lot more complicated.

I think that it also correctly pointed out that this whole thing vs symbol manipulator distinction is a lot more complicated.

While I instinctively believe things are more complicated than Hlynka's distinction, I became less and less convinced of this the more I waded through Bing's verbiage on the matter.

Not sure what the point of posting this was.

We're all quite capable of reading the post and coming to our own conclusions about it. I don't feel the need to outsource my thinking to anyone else, human or machine. I learn from other people, certainly, but I don't let them do my thinking for me. The purpose of the act of thinking is to determine what I think about something. Not to determine what someone else thinks.

"If men create intelligent machines, or fantasize about them, it is either because they secretly despair of their own intelligence or because they are in danger of succumbing to the weight of a monstrous and useless intelligence which they seek to exorcise by transferring it to machines, where they can play with it and make fun of it. By entrusting this burdensome intelligence to machines we are released from any responsibility to knowledge, much as entrusting power to politicians allows us to disdain any aspiration of our own to power. If men dream of machines that are unique, that are endowed with genius, it is because they despair of their own uniqueness, or because they prefer to do without it - to enjoy it by proxy, so to speak, thanks to machines. What such machines offer is the spectacle of thought, and in manipulating them people devote themselves more to the spectacle of thought than to thought itself. It is not for nothing that they are described as 'virtual', for they put thought on hold indefinitely, tying its emergence to the achievement of a complete knowledge. The act of thinking itself is thus put off forever. Indeed, the question of thought can no more be raised than the question of the freedom of future generations, who will pass through life as we travel through the air, strapped into their seats. These Men of Artificial Intelligence will traverse their own mental space bound hand and foot to their computers. Immobile in front of his computer, Virtual Man makes love via the screen and gives lessons by means of the teleconference. He is a physical - and no doubt also a mental cripple. That is the price he pays for being operational. Just as eyeglasses and contact lenses will arguably one day evolve into implanted prostheses for a species that has lost its sight, it is similarly to be feared that artificial intelligence and the hardware that supports it will become a mental prosthesis for a species without the capacity for thought. Artificial intelligence is devoid of intelligence because it is devoid of artifice."

-- Jean Baudrillard, The Transparency of Evil: Essays in Extreme Phenomena

The point of my exercise was that Bing Chat was able to understand Hlynka's text and produce a defense of humanities professors by actually improving on original arguments made by Hlynka. It produced the same true/false argument but it also provided a description of LLM shortcomings in more technical manner speaking about hallucinations or adversarial prompts.

So in that sense it was Hlynka's text that seemed more pomo compared to what GPT produced. Which I think is quite an interesting thing to observe. In the end I think at minimum the GPT + Human pair will outperform solo player in near future. At least in a sense that Human should know in what domains to completely trust GPT despite his own intuition.

The problem is that it's defense of humanities professors was exactly the sort of meaningless pastiche that you would expect if it was a pure symbol manipulator. Now you could argue that it sounds very much like the real arguments that would come out of the mouths of real humanities professors. But that just means Hlynka wins on both sides.

Except there nothing in my post about humanities professors being replaced by thing-manipulators. GIGO applies.

The author is suggesting that GPT-4 and humanities professors have similar goals and methods, and that they are both inferior to thing-manipulators who can challenge their claims with facts and data. He is implying that GPT-4 could replace humanities professors because they are both producing meaningless or misleading content.

It was about replacement of humanities professors by GPT-4 as opposed to thing-manipluators. But it also caught the tone of your thing vs symbol manipulators. And in that sense I completely agree about GIGO.

The part you're quoting says GPT would be a threat to humanities professors, not to the humanities. I'd wager that this would be a net benefit to the humanities and would actually constitute a meaningful form of the humanities catching a break.

The part you're quoting says GPT would be a threat to humanities professors, not to the humanities.

I don't think he was making such a fine-grained distinction.

The general thrust of his post was to set himself as a thing-manipulator apart from the symbol-manipulators. But the type of thinking on display in his post was precisely an example of the type of symbol-manipulation that he was deriding. I'll let him decide if he thinks this is a fair reading of his post or not.

I'd wager that this would be a net benefit to the humanities and would actually constitute a meaningful form of the humanities catching a break.

I won't speculate about what impacts GPT will or won't have on any aspect of the current university system.

In general, I don't share the instinctive hatred for academics that many here seem to have. Sure, a lot of them are leftists, but so what? Lots of people are leftists. If I had a meltdown every time someone was a leftist then I'd have a hard time functioning in modern society.

I enjoy reading the professional output of many humanities academics and I'd be quite happy to have them continue as they are.

In general, I don't share the instinctive hatred for academics that many here seem to have. Sure, a lot of them are leftists, but so what? Lots of people are leftists. If I had a meltdown every time someone was a leftist then I'd have a hard time functioning in modern society.

I don't think any sort of "hatred" people here have towards academics is "instinctive," and characterizing it as such is highly uncharitable. I think it's a learned antipathy based on observations and conscious analysis, and that this has very little to do with them being leftists. At best, the antipathy seems to be due to something that us upstream from them being leftists, i.e. the same sort of social/cultural forces that lead these academics to having sloppy thinking also leads to them being leftists.

I enjoy reading the professional output of many humanities academics and I'd be quite happy to have them continue as they are.

I'd wager that the humanities academics that produce professional output that are worth reading are ones who will be most resistant to replacement by GPT and the like. Whether they're completely resistant is an open question, I admit, but for the foreseeable future, I don't think there's much to worry about.

At best, the antipathy seems to be due to something that us upstream from them being leftists, i.e. the same sort of social/cultural forces that lead these academics to having sloppy thinking also leads to them being leftists.

Can you elaborate? Do you have any examples of this sort of "sloppy thinking" in mind?

I don't have any specific examples off the top of my head, but I'm thinking of the (I'm guessing largely unconscious and unintentional) peer pressure within the academia social/cultural spheres pushing people into adopting sloppy thinking in the form of being against rationality/logic/empiricism in favor of taking the word of people that one is predisposed to like. The peer pressure obviously takes many forms, but I'd guess mostly just in who is given higher social status versus who isn't, based on what sorts of opinions one espouses publicly, though some of it's certainly openly intentional directed bullying. These forces also tend to push people towards adopting (certain) leftist views.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats