site banner

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
Jump in the discussion.

No email address required.

Inferential Distance part 2 of ?: Minsky's Marvelous Minutia, or why I'm bearish on GPT

This post is a continuation of / follow up to my post on Inferential distance from a month ago, inspired by the recent discussions of GPT-4 and @ymeskhout's comments on prosecutorial immunity. I also feel like this might end up turning into a series, hense the "part 2" and the question mark.

Two things that came up in that previous conversation were a) the apparent differences between thing-manipulators and symbol-manipulators. That is people's whose job, hobbies, day-to-day life revolve around manipulating objects and those whose lives revolve around manipulating symbols/feelings. And b) the question of what constitutes a "hard" social problem, and how/why thing-manipulators and symbol-manipulators seem to have such wildly diverging opinions on that question.

For a bit of context my degree is in math but entering the field as I did, later in life having already spent 12 years in another career, I tended towards the more applied/practical side of the discipline. This tendency seemed put me at odds with a lot of my instructors and fellow students, especially the "nerdier" sort. That is those who were "nerdy" even by the relative high standards of nerdiness expected from someone pursuing an advanced degree in mathematics. for whatever reason showing an interest in applications was kind of looked down upon. To be fair, I did understand where they were coming from. From a young age we're trained to admire the brilliance of guys like Pythagoras, Leibnitz, Newton, Euler, Keppler, Einstein, Et Al. Afterall, why does anyone even bother to study math if not to follow in those men's footsteps and unlock the grand fundamental truths of the universe? In contrast, while the principals of kinematics, control laws, and signal processing, may be mathematically intensive they also come across as very pedestrian. Pure math guys seem to regard them with a sort of casual disdain, the sort of thing you delegate to unpaid interns and teachers' assistants. Meanwhile truth is you can build yourself a pretty good career working on control laws and signal processing, just not in academia.

This brings us to the question of what constitutes a hard problem. If you spend enough time working in robotics or signal-processing, you'll eventually come across Moravec's Paradox. The paradox is best summed up by this xkcd comic from 2014, specifically the alt-text which reads...

In the 60s, Marvin Minsky assigned a couple of undergrads to spend the summer programming a computer to use a camera to identify objects in a scene. He figured they'd have the problem solved by the end of the summer. Half a century later, we're still working on it.

...the "paradox" being that many functions that we consider baseline, and accordingly take for granted, are in fact extremely complex and computationally intensive. Whereas much of what we might label "higher reason" is actually quite simple and requires very little in terms of memory or processing power.

It turns out that it's relatively easy to teach a computer to play chess better than a human or to come up with mathematical proofs that are both novel and correct. And yet, after 60 years, despite the truly massive advances in both hardware and software represented by projects like stable diffusion Minsky's problem remains far from solved. In practice, you can pretty much graph straight line between the simpler a task seems/earlier a it appears in the evolutionary enviroment, to how hard it will be to replicate. Playing chess is easy, Bipedal locomotion is difficult. Bipedal locomotion only seems easy to creatures like you and me because we've been doing it since we were two-years-old, and our ancestors spent millions of years refining the techniques and bio-mechanics that were bequeathed to us as infants.

What does this have to do with anything? My answer is that I feel like a recognition/understanding of Moravec's Paradox is one of the major components of inferential distance between myself and most others both in the rationalist movement, and in academia. It is why I am reflexively skeptical of grand unified social/political theories. and It is also why I remain deeply skeptical of GPT and the oncoming AI apocalypse it allegedly represents.

One claim you'll see guys like Elizer Yudkowsky, Bryan Caplan, and posters here on TheMotte make on a semi-regular basis is that "GPT knows how to play Chess". But if you press them on the topic, or actually look at chess games that GPT has played it becomes readily apparent that GPT makes a lot of stupid and occasionally outright illegal moves (eg moving rooks diagonally, attacking it's own pieces, etc...). What this demonstrates is that GPT does not "know how to play chess" at all. At least not in the same sense that Deep Blue or my 9-year-old can be described as "knowing how to play chess", or AlphaGo can be described as "knowing how to play Go".

Furthermore, once you start digging into their inner workings this lack of "knowing" appears to be a fundamental weakness of the Large Language Model architecture. At the end of the day it's still just a regression calculating the next most plausible word (or in the case of GPT-4 string of words) based on the correlations found in it's training data. Granted GPT-4 is certainly a step up from GPT-3 in terms being able to pass as human. The shift towards correlating longer statements rather than individual words seems to have plastered over a lot of the jarring discontinuities that made GPT-3 generated posts so easy to pick out. In contrast GPT-4 can actually kind of pass for human from the proverbial 50 ft away. Unlike prior GPT iterations, identifying it actually requires a level of careful reading or some sort of interaction.

Eugene Volokh's posts on Large Libel Models probably deserves a discussion of their own but INAL and not really interested in questions of liability. In any case he ends up running into the same issue with GPT that I did. Users here talk about instances of GPT "lying" or "hallucinating" and how to reduce the frequency of such instances, but the conversations inevitably devolve into self-referential nonsense because neither of these terms really describe what is actually happening. In order to "hallucinate" one must first be able to perceive. In order to "lie" one must first understand the difference between true and false. and GPT possesses neither. Simple fact is ask GPT for five examples of prosecutorial misconduct complete with citations and newspaper quotes and it will provide the names of five prosecutors, their alleged crimes, some juicy quotes, and supposed case numbers. However while the names provided might actually be real prosecutors, and the media outlet quoted might be a real outlet, if you actually look up the court records or try to find the quotes you're going to come up short because the example was not something that was pulled out of memory and provided, it was "generated" form the prompt in exactly the manner that a Large Language Model is designed to do.

to be continued...

edit: fixed link

...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).

Which honestly sounds a bit like something I would come up with to try to fool the teacher into thinking I read the books...

...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.