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.
Jump in the discussion.
No email address required.
Notes -
...and now the conclusion
From the outside it might seem like a straight-forward fix to just add a line to the prompt that says "only provide real quotes / true statements". but to implement such a function requires imbuing GPT with an understanding of the difference between "true" and "false" and between "real" and "imagined". That is a real hum-dinger of a problem. It is such a hum-dinger of a problem that there is an entire branch of philosophy devoted to discussing it, that being Epistemology. As simple and foundational to computer science as the concept of a boolean might be, this is not a problem I see getting solved anytime soon.
Accordingly, when i see some AI-doomer post about how GPT-4 has passed the BAR exam in some state or gotten an A on Bryan Caplan's mid-term economics exam, my first thought is in not "oh shit here comes the fast take-off". It's more "and just how diligent were people grading the papers being?". In one of those threads the topic of grading on a curve came up and the question was asked why should we ask professors to go through the effort of calibrating tests to the material when it is so much simpler/easier/more efficient to ask a spread of arbitrarily difficult questions and award the top x% of answers 'A's. I ended up biting my tongue at the time because my knee-jerk response was something to the effect of "because that's fucking retarded and ultimately defeats the purpose of even administering a test in the first place" But upon a moment's reflection I realized that was a very "thing-manipulator" thought to have.
Thus we come back to the issue of inferential distance. I struggle to articulate just how brain-meltingly stupid and arbitrary the whole concept of "grading on a curve" seems to me. But I also recognize that grading on a curve is a widely accepted practice. From this I infer that my concept of a test and it's purpose is wildly different from that of Bryan Caplan and a lot of other users here on theMotte.
Perhaps this is my "thing-manipulator"-ness talking, but it seems intuitively obvious to me that if a teacher or professor is grading on a curve, they are not grading you on your capability or knowledge of the subject. and if they are not grading you on your capability or knowledge of the subject what re they grading you on? It seems to me that if a teacher and their students are on their game it should be possible for 100% of a class to earn a 100% grade. Just as if manufacturing is truly on the ball it should be possible to achieve a 100% pass rate from the QA department. Granted this never actually happens in the real world because life is imperfect but it's something to strive for isn't it? A man might just find himself a member of the '72 Dolphins.
What is the purpose of a test or inspection in the first place if not to verify capability?
Ironically, I think the real existential threat posed by GPT is not to humanity but to humanities professors. I would argue that if Caplan had been grading his students on their knowledge and understanding of the material (as he ought to have been from the outset) he wouldn't have found himself in this pickle. That GPT-4 got an A on Caplan's mid-term is not evidence that GPT-4 understands economics or history, it's evidence that Caplan does not understand his role as a educator. GPT is essentially the prefect Post-Modernist, and in so being it is exposing post-modernism and the entire edifice of contemporary academia as the farce it's always been.
The cynical bastard in me suspects that the reason "Symbol-Manipulators" seem to be so freaked out about GPT is that it represents a fully-automated-luxury-gay-reductio-ad-absurdum of everything that they think they know.
I’ll repeat something I said elsewhere. Tests of subject matter are usually objective tests of concepts. If. You know the concepts you pass. Passing Caplan’s economics test is domain limited — if it had trained on basic concepts it would probably do pretty well because while it requires knowledge of the concepts of economics and how to apply them to economics problems, it doesn’t require understanding this. Knowing how to use the Pythagorean theorem to find the shortest arm of a right triangle given a hypotenuse and the long side isn’t hard. Rearrange the equation and go.
Projecting the future from a given dataset using a theory would require understanding the data and the bits that are relevant and figuring out how the theory and the data can be used to find the answer. So a question like “using the complete set of all the Dune series of books and Peter Turchin’s theory of cliodynamics, project the future of the universe 30,000 years into the future”. Very little in the the books would be useful in making the projections (although I suppose if you count the mention of sand worms and spice or references to a famine those would be useful). ChatGPT would have to figure that out though, as well as just how much of the action and characters are irrelevant to the project. But the process of figuring all of this out requires understanding what the books are saying and what they aren’t, and requires understanding cliodynamics on a level above “insert numbers into the equation and go.”
This is what knowing and understanding would seem to mean: not just being able to manipulate words and numbers and equations, but to do so with a sense of what the numbers or words mean. To put it in the context of the more famous Chinese Room thought experiment— in order for the person in that room to understand the questions and the answers, it’s not enough to simply pattern match 我 with 李张 I would have to understand that I’m telling the outside world that “I” am named “Li Zhang”. If I cannot do that, if I only understand in the sense of seeing one symbol and outputting another without knowing why the correct answer to X is A and not C, I don’t understand it.
Edit: just for kicks I asked ChatGPT about the future of the dune universe:
Dune is a rich and complex universe that has captured the imaginations of generations of readers. As an AI language model, I can imagine what the Dune universe might look like 30,000 years after the end of Dune Chapterhouse, based on the information available in the books and the various adaptations.
Assuming that the long-term goals of the Bene Gesserit and their sisterhood of Mentats were achieved, the human race could have evolved into something more than we can currently imagine. They would have mastered advanced technologies and could harness the power of the Guild Navigators and the sandworms to travel across space and time. The planet of Arrakis could be transformed into something entirely different, devoid of the sandworms or even turning into a lush, forested world with oceans and rivers.
The descendants of the Atreides bloodline like Leto and Ghanima would have spread out across the galaxy, establishing themselves as new ruling dynasties. Implications of a far reaching society where humans have been colonized, terraforming planets and form all sorts of political groups and religions.
On the political front, the Imperium could have been replaced by a new system of government. Perhaps, the Butlerian Jihad against the thinking machines would have been avoided, and intelligent machines like the Ixians and the Taurid would have prospered. Alternatively, humans could have replaced the thinking machines with new technologies, and the entire social structure must have dissolved due to the rapid technological advancements.
In conclusion, the Dune universe 30,000 years after the end of Dune Chapterhouse is a realm of endless possibility, and it holds untold wonders and horrors beyond our current comprehension. As an AI language model, it is beyond me to predict the exact path the universe might have taken, but one thing is for sure: it would be a fascinating and dynamic place to behold.
(Which honestly sounds a bit like something I would come up with to try to fool the teacher into thinking I read the books. For example, Leto actually became a worm and was thus sterile, he had no natural descendants. Also, I noticed that no mention of specific plans by the Benefit Gesseret, Mentats, etc. and the Butlerian Jihad happened 10,000 years before the first book, and Ixians aren’t machines).
...but hadn't actually read the books.
and that "hasn't actually read the book" quality is exactly what i feel like Volokh and I both latched onto, but reading through the other replies I've gotten the impression that most users here either do not understand or do not consider having "read the book" to be relevant to parameter when discussing it's contents.
Like I said in the OP, GPT is effectively the "perfect post modernist", it's literally "all talk" and no thought. Theres no need to kill the author when the author was dead from the beginning.
What it looks like to me is that it knows the groups that should be mentioned (mentats, the Guild, Ixians, Bene Gesseret) but it doesn’t know what they are or what they want. It’s also fairly confused about the people and the timeline. It knows that those events happened, but not the order, and apparently doesn’t know that a lot of the stuff it’s predicting to happened 30K years after chapterhouse had already happened.
Which to mean points to ChatGPT-4 as a Chinese Room. It knows vaguely to use terms like Sandworm, Mentat, and Arrakis when talking about the Dune series. It knows to talk about evolution. But it doesn’t understand what things mean; the Bene Gesseret don’t mean anything to the chatbot.
More options
Context Copy link
More options
Context Copy link
That all definitely sounds like what I would have written if I had the most vague impression of the franchise.
More options
Context Copy link
More options
Context Copy link
Based on your teaser last week I was expecting a revisit of Christianity and the Western Tradition. Isn't Christianity, in your model the foundation of civilization, the ultimate creation of Symbol-Manipulators?
No, because in my model God is real.
More options
Context Copy link
More options
Context Copy link
Being able to produce truth 100% of the time is a hard problem. Being able to produce truth in the subset of cases which are easy to recognize by a human as being untrue is not such a humdinger, and the latter is what people are requesting when they ask for no hallucinations.
There's a big difference between philosophical concepts of abstract truth, and "when it names a Star Trek episode, this had better be the name of an actual episode".
Is there? It seems obvious to me that the latter is down stream of the former.
More options
Context Copy link
I don't think he was trying to say that the problem is being able to produce truth 100% of the time. The problem is understanding what it means for something to be "true" or "false" in the first place.
Same answer. We don't have a general understanding of true and false, but we know whether some things are true and false, and ChatGPT fails even on that subset of easy things that we do understand.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
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.
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.
More options
Context Copy link
I think he would not disagree. I ran Hlynka's text through Bing Chat and this was its summary regarding the humanities professor part:
I asked about some counterarguments and here is what it came up with:
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:
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:
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.
More options
Context Copy link
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.
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.
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.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
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.
-- 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.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Except there nothing in my post about humanities professors being replaced by thing-manipulators. GIGO applies.
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.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
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.
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 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.
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'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.
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.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Caplan had a very strong incentive to fail the AI. He publicly bet against AI passing his exams a few years back. He has a very long and unbroken streak of victorious bets, and it looks like this one is the first one that he will actually lose.
The obvious couter observation is that Caplan having an incentive to fail the AI is orthogonal to whether Caplan's exam actually measures a student's understanding of economics.
More options
Context Copy link
More options
Context Copy link
That was me. And this complain would make a lot more sense if education was training people to actually do the tasks they perform at their jobs. But it doesn't. Calc tests and econ tests are just academic-themed IQ tests, because nobody actually uses calc or econ in their jobs except for a tiny minority, and that minority could be easily trained on the job instead of outsourcing the task to a 4-year high institution that charges tens of thousands of dollars for the privilege. Employers are using degrees and GPAs to select the top x% employees, not to verify that the student has achieved an objective standard of excellence in subject y (otherwise, would use nationwide standardized tests instead of whatever crap the professor came up with, in which case, WOULD make sense to effortfully calibrate objective passing grades against the material).
From "The Magic of Education" by Bryan Caplan:
More options
Context Copy link
I don't think it's possible to conclude this. GPT can pass a simple math test, for example, does this mean a math teacher does not understand his role?
More options
Context Copy link
And if you look at the actual content of the test, you will note that you are entirely correct that it's not a test of "how well have you internalized the principles of economics", it's a test of "do you agree with Bryan Caplan's politics".
"Do you agree with [professor]" is the subject of every university-level exam.
Oh come now.
I had a philosophy class in undergrad with a professor who had published extensively on a particular topic in philosophy of mind, and he was quite proud to be known as one of the leading experts in his particular sub-field. For my final paper in the class I ended up disagreeing extensively with his views - and he let me know this by writing a thorough rebuttal for almost every paragraph in my paper - but he still gave me an A because he thought my paper was well argued.
More options
Context Copy link
More options
Context Copy link
some of the questions are weirdly worded too, like this one
He means asymmetric information or default structure that benefits the borrower , thus incentivizes higher education, which it's plausible he is right. But it's more like an article of faith than something rigorous.
More options
Context Copy link
More options
Context Copy link
This post explains the source of much of my skepticism of AI better than I could. But the idea of LLMs as ultimate postmodernists insofar as they are masters of language and nothing else is a key insight that I'm mad I didn't think of first.
Of course this is no accident since the very idea is just a sophisticated generalization of Markov chains which were famously great at generating pomospeak.
But it is getting to the level where it might have practical utility now.
Provided nobody finds an unfavorable equilibrium in the AI detector arms race, or at least none that also would allow human nonsense, this tool could be the final solution to the problem of credentialism.
Why indeed listen to the academic if you can replicate him with AI well enough that you could get his diploma without needing but to press a button? And then we can merrily go back to judging shamans through the only metric that matters ultimately: whether the hexes work or not.
...and that's a bingo. (Insert your preferred Christoph Waltz meme as you see fit.) ;-)
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link