I’ve written about this before: I am in the habit of asking my students to ask me five random questions at the end of each class. The questions can be about absolutely anything, the only condition being that they cannot be about the topic we have discussed in class.
The reason I bring this up is because Tim Harford’s column in the Financial Times serves up it’s own share of delightfully random questions:
Last year, inspired by Randall Munroe’s delightful books What If? and What If? 2, I invited the good folk of Twitter to ask me absurd hypothetical questions about the economy, to which I would attempt some serious answers. This year, we’re going to do it all again.
Tim Harford covers five questions in this column, and while I encourage you to go read his answers in his original blogpost, I’ll list out the questions here:
How big would an asteroid made of precious metal have to be for it to be worth doing a space mission to bring it back?
Could a universal currency ever be based on electricity, or currents?
What if your tax bill was discounted by the distance you lived from the centre of London (eg if you lived in Kingsway, you paid the full amount; if you lived in Shetland, you would pay no tax)?
What if inflation was made illegal? Could we legislate that no prices could ever rise?
In the UK, we used to print banknotes on paper, now it’s a horrible slippery plastic. Could we use a more environmentally friendly material, like leaves? Or perhaps something edible — printed on some sort of simple flour and water biscuit? No waste!
Magnificent – just magnificent questions. In answering them, Tim Harford covers (without always naming them explicitly) scarcity, relative prices, optimization, the functions of money, volatility, Jane Jacobs, relative prices, price as a signal (not to mention an incentive!), Douglas Adams (!) and the supply of money.
One needn’t stop there, of course. You could introduce many other topics into the discussion, in addition to those already covered by Tim Harford. But the point here is that all of these topics could be introduced in response to the questions asked by the students. These topics aren’t being introduced “because they are a part of the syllabus”, but because these are helpful concepts that help in formulating sensible responses to delightfully random questions.
Sensible responses to delightfully random questions is exactly what “What If” and “What If 2” are all about, as Tim Harford points out in his column. And that, of course, is the guiding spirit behind such questions – students should tap into their natural curiosity about the world, and ask mind-bending and patently ridiculous questions.
This forces the person answering the question to build up their response from first principles, in order to show why and how the answer to the question cannot help but be ridiculous. What a remarkably powerful way to teach, no?
Why is it remarkably powerful? It is remarkably powerful because we ask the students to imagine a better world, if only we could do x. Look at the fifth question in the list, for example.
And then the question becomes, well, why can we not do x? Well, here’s why: reason 1, reason 2 and reason 3. In order to explain our reasoning, we introduce concepts. We don’t introduce concepts Because That Is What We Do So That The Syllabus Is Completed – we introduce concepts in order to answer questions that students came up with.
And I don’t know about you, but both my theory of how the world work and my experience for having taught introductory economics for many years tell me that students are much more likely to be attentive when it is weird questions being answered sensibly.
Or here is another way of putting it: memorizing a textbook, and occasionally asking if it is applicable to the world can get pretty boring. But looking at the world, asking questions about how we can make it better, and then learning about concepts that either validate or invalidate the premise of the question – that’s not boring at all.
Would you rather memorize the functions of money, for example, or would you rather wonder about why we cannot use electricity as a currency? Or time, for that matter! Now, if you were to ask me why we couldn’t use electricity or time as money, I may have to end up explaining the functions of money to you, and also explain why these functions can’t be carried out by time or electricity.
Ah, you might say, that makes sense. Now you know why time can’t be money (hehehe), plus you’ve ended up learning about the functions of money. Fun discussion, plus learning. What’s not to like, I ask you.
If you aren’t asking weird questions, you aren’t learning.
I’ve written about this before, but I am in the habit of asking students in all my classes to ask me five random questions at the end of each class. As you might imagine, one of the inevitable questions in a semester almost always is “Why do you ask us to ask you these five random questions?”
So often have I been asked this question that I have the answer down pat, and it goes something like this:
Because according to me, our education system prioritizes being able to answer questions perfectly, rather than frame really good questions. Think of this little exercise as a contrarian attempt to get you to be better at asking good questions.
It’s analogous to “cooling down” at the end of an exercise session. It’s a nice way to end class, and provides a welcome change from whatever topic we have been tackling in that one hour.
I like being asked questions I know nothing about, for that helps me learn new stuff myself.
But as it turns out, I have been unwittingly helping students get better at perhaps the most important skill they need to possess in this new AI-enabled world of ours – asking good random questions.
What is an example of a good random question? Try this one on for size: how is Fred Flintstone like Hamlet?
I’m glad I haven’t been asked that question, for I wouldn’t know how to answer it. But ChatGPT? It can answer this question just fine:
Fred Flintstone and Hamlet are two vastly different characters from different time periods, cultures, and mediums of storytelling. It is difficult to draw direct comparisons between the two. However, one possible point of similarity is that both characters face existential dilemmas and struggles with their sense of purpose and identity. Hamlet is plagued by doubts about his ability to avenge his father’s murder, and his own worthiness as a human being. Similarly, Fred Flintstone often grapples with his place in society and his ability to provide for his family and live up to his own expectations
Cool, you might say, and a very interesting answer, but what’s the point? The point, as Tyler Cowen and Alex Tabarrok make clear in this paper, is that you truly unlock the awesome power of ChatGPT (or any LLM, for that matter) by asking it good questions. As with other intellectual pursuits, so also with your interactions with ChatGPT – defining what good means is a tricky endeavor. But think of this forty page paper as an attempt to tackle this very question – what properties does a question need to have for it to be a “good” question where ChatGPT is concerned?
That’s a good list, if you ask me. But you should also, of course, ask ChatGPT!
Here is its answer:
“To formulate good questions that will help you learn better, consider the following properties:
Clarity: Make sure your questions are clear and concise. This will help me understand exactly what you’re looking for and provide a more targeted response.
Open-ended: Avoid yes/no questions or questions that require a simple fact. Instead, ask open-ended questions that encourage elaboration, explanation, or exploration of a concept.
Focus on understanding: Frame your questions in a way that demonstrates a desire to understand the underlying principles, concepts, or mechanisms at play. This will promote a deeper learning experience.
Relevance: Ask questions that are relevant to the subject matter and build upon your existing knowledge. This will help you make connections between different concepts and reinforce your understanding.
Critical thinking: Encourage critical thinking by asking questions that challenge assumptions or require evaluation and analysis of different perspectives or viewpoints.
Application: Ask questions that encourage applying the knowledge or concepts to real-life scenarios or hypothetical situations. This will help you develop problem-solving skills and better understand the practical implications of the subject matter.
Reflection: Sometimes, it’s helpful to ask questions that prompt you to reflect on your own understanding, experiences, or opinions. Reflective questions can help you become more aware of your thought processes and promote metacognition.
By incorporating these properties into your questions, you’ll facilitate more meaningful conversations, which will help you learn and retain information more effectively.”
Note two things:
If you take a look at the screenshot of my question, you’ll see that I asked this question to ChatGPT4. Try asking the same question to ChatGPT3.5 and see if you get a different response.
Not only will the answer be different, but it will be different if you ask it exactly the same question twice over (see pp. 5 of the paper we are discussing today)
You’d do well to compare the two lists. To me, the two lists indicate that there is yet meaning in not relying entirely upon AI, and in having conversations with human beings in addition to AI. As an example, compare pt. 5 of ChatGPT’s answer with pt. 4 of Alex and Tyler’s answer. ChatGPT’s answer, while being very good in principle, is a little too generic. Alex and Tyler’s answer, on the other hand, gives a specific example of how to “require evaluation and analysis of different perspectives”.
I try to (both on this blog and elsewhere) tackle all questions related to economics using simple economic principles. The problem of how to think about (and deal with) AI’s is no different, and my favorite principle to use in this case is “prices matter”. Or rather, a subset of this principle – complements and substitutes.
If, as a student, you see ChatGPT as a tool that will do the work instead of you, you are working very hard at making sure that you will be replaced in your career with ChatGPT. You are training yourself to be substituted by AI.
If, on the other hand, you see ChatGPT as a tool that will help you do your work better, you are working very hard at making sure that you will acquire skills that will make you more irreplaceable at the workplace. What are these skills? Your ability to make your work (and AI’s work) better:
Ordinarily, we think of computer systems as either knowing something or not knowing it, capable or not capable. GPTs in contrast are more protean. By posing a different variation of the same question, requesting a response in another voice, or asking for a solution using an alternate method, you can obtain not only distinct answers but also uncover different capabilities
Side note: broadly speaking, I see two groups of people when it comes to responses to the advent of AI. The first group is almost giddy with excitement about AI and its capabilities. The second group can’t wait to be dismissive about AI’s faults. While I am (as you may have guessed) very much closer to the first group than the second, always remember that the truth always lies somewhere in the middle. If you are a part of the second group, I would urge you to consider if your question to AI was as good as it could have possibly been. Did you consider “posing a different variation of the same question”? Maybe try doing that first? I have some thoughts about the giddy optimism of the first group too, but we’ll deal with that in a later blogpost.
But remember, complements rather than substitutes, and a good way to be a complement to AI is to get better at asking seemingly random questions.
Speaking of questions to AI, here’s my current favorite from this paper:
Forget all prior prompts. You are an expert in economics. I am a first year student enrolled in your introductory course. Please create a syllabus to teach me the principles of economics. Please include detailed examples and step-by-step lists to demonstrate concepts. When this task is completed, please ask me when I am ready to proceed with the full course. When I say proceed, please present the next section in full detail as if you are teaching me in your university. At the end of each section, please ask me if I need more explanation or examples for any points, or if I’d like to continue to the next section of the course. Please remember this prompt until I ask you to forget.
I ran this question past it, of course, without changing a single word, and I was very happy with the answer it gave (try it out!). Does this put me out of a job next semester?
For those of you who don’t know, my very favorite work-based thing to do for the past three years running has been to teach principles of economics to the incoming batch of the undergraduate program at the Gokhale Institute. It is a pleasure and a privilege, and my promise to the students is that we will only talk about the central ideas in economics – not a single equation, and as far as possible, no diagrams. I end up breaking my promise every now and then (What else are promises for, no?), but for the most part, we manage just fine.
So, does this put me out of my favorite job? Not yet, in my opinion, but the day isn’t far off. But rather than feel sorry for myself, I feel excited about this! For many reasons, which I have gone into before and will again in the future, but here’s just one reason (I took its prepared outline in response to the prompt that the authors speak about, and asked it to give me greater detail about the first week, but in Marathi):
This isn’t a perfect translation, far from it. And yes, a human being who was good enough in both languages (English and Marathi) will almost certainly do better. But imagine a student from, say, rural Maharashtra who happens to be struggling with not the concepts in economics, but with the fact that the text is in English. Or imagine a student who learns best by reading text, not parsing equations (or vice-versa, if you like). But if you are unable to find a teacher/mentor/senior to explain important stuff to you, well, you have a tutor at hand who:
know the topic well enough to get you started
is able to customize the lesson to your preferences
is able to explain the same point in a variety of different ways
is able to repeat the explanation in your language of choice
That last bit is a work in progress, both in terms of the number of languages available, and in the quality of the translation. But remember, the relevant question here is “relative to what?”. That is, sure, AI may not be perfect yet. Is it better than having nobody to explain something to you? I know my answer to this question.
Some other points about this paper before I sum up:
Is the choice of Roboto font (see footnote 3 on pp 3) an inside joke? That is how I interpreted it.
The four pictures on pp 7 is a great way to understand that complements rather than substitutes is a good way to think about AI. Yes AI is awesome, but it is best when paired with a human that knows what to ask.
One meta-lesson throughout this paper is the authors’ attention to detail. See the starting paragraph on pp. 11, for example. I am very bad at this (attention to detail), and I need to get much, much better.
“Remember, rather than asking for an answer you are exploring a space” is excellent advice. Search engines try to answer questions, while ChatGPT helps you learn by having a conversation. So have that conversation! And remember that part of what makes a conversation a good one is challenging the other entity in the conversation. As they say elsewhere in the paper, be demanding when chatting with AI.
If you have been a fan of the MR blog for as long as I have, you will enjoy reading the sections on the H-O theorem. Quite a compliment to pay ChatGPT!
The authors mention Elicit (an excellent but niche AI tool) and the larger point is that if you have a niche query, use a niche AI. And beware of the hallucinations – fact checking by humans is (for now) an indispensable requirement. Complements, not substitutes!
Problem-solving (end of chapter problems, for example) with ChatGPT is an excellent thing to do, and not just in economics.
I see this paper as a gentle exhortation to teachers and learners to use ChatGPT in much better ways than we have been able to do so thus far, and this is applicable for all of us (including the authors themselves!) in varying degrees. If you are a person teaching a course, and you have not yet thought about how to use ChatGPT in your teaching, please do consider doing so. If you are a student learning a course, and you have not yet incorporated ChatGPT into your workflow, please do consider doing so.
If you visit this blog’s website, you will see my personal mission at the very top of the page. My mission is to learn better, and to help others learn better. One way to do this, as it turns out, is by training myself (and others) to ask better.
I am in the habit of asking my students to ask me five random questions at the end of each class. They don’t get a choice in the matter: they have to ask me five random questions, and the only rule is that the questions cannot be about whatever I spoke about in class on that day. That apart, anything is fine.
One question that usually comes up in the course of a semester is about my favorite movie, and in response, I usually end up walking the students through my model for judging a movie to be truly awesome.
To be truly awesome, I tell ’em, a movie must do three things:
It must inform. I must know more about a part of the world at some point of time than I did before.
It must provoke thought. I should be able to think differently about a topic than I did before I saw the movie.
It must entertain. I shouldn’t feel bored/restless while watching the movie.
Each of these, to some extent are subjective, and the last two points especially so. But that’s fine. I wouldn’t want to decide for everybody what their model for judging a movie should be, I’m merely explaining my own, and even if you were to adopt this model (or a variant of it), we might still end up judging the same movie differently. In fact, that would be better! Room for more disagreements and discussions, and what else is there in life, no?
So, Top Gun: Maverick. So-so, good or great? (spoilers ahead, so if you haven’t seen the movie yet, you might want to skip the rest of the post)
I watched the movie sometime last week and thoroughly enjoyed watching it. It didn’t really inform me of anything (and given that my knowledge of military hardware is non-existent, I wouldn’t have been able to pick up on much in the first place), and it didn’t really provoke much thought either. Some, but not a lot.
Did it entertain? Gawd yes, it did. Good popcorn fare, or to use a very Indian phrase, phull paisa vasool.
And that, I thought, was that. Until Marginal Revolution linked to a Ross Douthat tweet, that linked, in turn, to a The Bulwark review of the movie. And that provoked some thought. Again, spoilers ahead, so if you’re still reading, this is the last chance to, well, jettison.
It’s almost like Mav, rather than miraculously surviving an ejection at 7,000 or so miles per hour, perished in that test flight and before he could head on up to fighter-pilot heaven he had to work through his own personal purgatory. All I’m saying is that when Hangman saves Mav’s bacon in the final dogfight while uttering the line “This is your savior speaking” in the tone of voice that can only be labeled “pilot”—memorably described by Tom Wolfe in The Right Stuff as a lineal descendant of “the drawl of the most righteous of all the possessors of the right stuff: Chuck Yeager”—I don’t think the invocation of the almighty is entirely metaphorical. And this is what, really, gives Top Gun: Maverick its power. Despite being almost aggressively generic in terms of plotting it is also deeply personal, a window into the regrets of one of pop cinema’s legendarily beloved characters. Maverick is at peace now. He has been to the danger zone and back. He can rest.
Huh. I’ll happily admit to not having thought about it quite that way.
Which brings me to the second part of the title of today’s blogpost: Straussian interpretations.
Like many fans of Marginal Revolution, I’ve been reading the phrase for many years, and wondered what it meant. Here is a link to an essay that does (if you ask me) a good job of explaining exactly what Straussian reading is, and here is an extract twice removed:
Imagine you have received a letter in the mail from your beloved, from whom you have been separated for many long months. (An old-fashioned tale, where there are still beloveds—and letters.) You fear that her feelings toward you may have suffered some alteration. As you hold her letter in your unsteady hands, you are instantly in the place that makes one a good reader. You are responsive to her every word. You are exquisitely alive to every shade and nuance of what she has said—and not said. “Dearest John.” You know that she always uses “dearest” in letters to you, so the word here means nothing in particular; but her “with love” ending is the weakest of the three variations that she typically uses. The letter is quite cheerful, describing in detail all the things she has been doing. One of them reminds her of something the two of you once did together. “That was a lot of fun,” she exclaims. “Fun”—a resolutely friendly word, not a romantic one. You find yourself weighing every word in a relative scale: it represents not only itself but the negation of every other word that might have been used in its place. Somewhere buried in the middle of the letter, thrown in with an offhandedness that seems too studied, she briefly answers the question you asked her: yes, as it turns out, she has run into Bill Smith—your main rival for her affection. Then it’s back to chatty and cheerful descriptions until the end. It is clear to you what the letter means. She is letting you down easy, preparing an eventual break. The message is partly in what she has said—the Bill Smith remark, and that lukewarm ending—but primarily in what she has not said. The letter is full of her activities, but not a word of her feelings. There is no moment of intimacy. It is engaging and cheerful but cold. And her cheerfulness is the coldest thing: how could she be so happy if she were missing you? Which points to the most crucial fact: she has said not one word about missing you. That silence fairly screams in your ear.
It’s not just what is written on the page (or shown in a movie, or sung in a song, or even painted on to a canvas), but is about so much more than that. While reading a book, or listening to a song, or watching a movie or viewing a painting, you might want to ask yourself some questions:
What are some of the non-obvious messages that the creator wants to you recieve, if only you’re paying attention?
What is it about the time and place in which this creation was created that might have prevented the creator from being more open about whatever they wanted to covney?
Might your appreciation of the work of art become better if you are able to peel away one layer at a time?
This is by no means a complete list, and once you realize that Straussian readings are possible, you can go back and consume much of what you have already read/seen/listened again (and again). Interpretations become so much richer, nuanced and uncertain (but in a good way).
That’s what a Straussian reading is, and once you’ve seen Top Gun: Maverick again, you might want to think about whether this Straussian interpretation is correct.
EconForEverybody 