His last letter was an update on a serious health issue. I care. It's not supposed to be a yuck fest, especially inorganic AI sludge.

No job is special, even though many programmers like to think of themselves as so. Everyone must learn to adapt to a changing world, just as they did a hundred years ago at the turn of the century.

There may not be many people whose professional job is using a typewriter, but there are still tons of writers.

Things that won't be automated anytime soon, like plumbers or electricians.

Or double down on applied ML?

> This fallacy seems to be brought up very frequently, that there are still blacksmiths; people who ride horses; people who use typewriters; even people who use fountain pens, but they don't really exist in any practical or economical sense outside of 10 years ago Portland, OR.

Did you respond with a fallacy of your own? I can only assume you’re not in or don’t have familiarity with those worlds and that has lead you to conclude they don’t exist in any practical or economical sense. It’s not difficult to look up those industries and their economic impact. Particularly horses and fountain pens. Or are you going by your own idea of practical or economical?

The Mechanics Institute, where craftsman learned and offered their wares in my town, was founded in 1801.

Its still here, today.

I wouldn't dismiss an industry based on business failures. The restaurant industry still exists, despite it being almost a guarantee that you will fail.

There's also stores with hand-knitted clothes and bears, sculpters and painters.

Yes, all of these are niche - but they survive because they embrace a different business model.

Right, nobody needs cabinets or doors because... AI. /s

I'm a professional woodworker. One-off tables in a garage might not be a great business, but millwork, built-ins, and cabinetry in homes is a great business. You're likely not exposed to cabinet or architectural woodwork shops that build high-end homes, or that just do renovation for that matter.

Bro, there is a HUGE market for one off software projects for lots of money.

That's a common usage of a rhetorical question. You ask it and then you answer it.

This doesn’t make sense to me. Why would you want something like this? What is it exactly that you expect from such a finetuned model that you cannot get from a frontier general purpose model?

Submitted for your amusement, my part in the downfall of the titanic book-shilling intellect that is EconGOAT GPT-4:

  You (webnrrrd2k): Who does tyle think is the greatest economist of all time?

  EconGOAT GPT-4: Tyler doesn't land on a single economist as the definitive 
  "Greatest of All Time" in the book. Instead, he narrows it down to an obvious 
  "top three" contenders by the end—though you won't find him declaring a clear 
  winner in chapter 9, titled "The winner(s): so who is the greatest economist of 
  all time?". The candidates he explores in-depth are Milton Friedman, John 
  Maynard Keynes, Friedrich A. Hayek, John Stuart Mill, Thomas Robert Malthus, and 
  Adam Smith. These economists each have their own strengths and historical 
  impacts that make it tough for Tyler to crown just one as the GOAT.

  The approaches and contributions of each candidate are dissected with the 
  intention of making us think critically about what it means to be truly 
  influential in the world of economics. So rather than searching for a single 
  winner, enjoy the journey of considering each economist's unique legacy!

  You (webnrrrd2k): Who are the winners in chaper 9?

  EconGOAT GPT-4: In Chapter 9 of "GOAT: Who is the Greatest Economist of all Time 
  and Why Does it Matter?", Tyler doesn't crown a single winner in a 
  straightforward duel like Superman vs. Flash. Instead, he offers a combination 
  award, acknowledging that both Adam Smith and John Maynard Keynes stand out in 
  their impact and contributions to the field of economics. Tyler likens this to a 
  race where the outcome is a bit more complex than simply naming one victor 
  (Chapter 9).

  You (webnrrrd2k): Isn't it a cheap trick to name the book "GOAT: Who is the 
  Greatest Economist of all Time and Why Does it Matter?" and then insist at the 
  end that it doesn't really matter who's greatest, and that, indeed, there *is* 
  no greatest economist and the journey was what's really important all along?

  EconGOAT GPT-4: Ah, you've caught on to Tyler's crafty ways! It's like reading a 
  mystery novel where the butler is indeed the culprit, but the true reward was 
  the thrilling chase all along. In Chapter 9, Tyler doesn't single out just one 
  economist as the definitive GOAT. Instead, he offers an intriguing discussion 
  about the strengths and weaknesses of each candidate, emphasizing that the true 
  value lies in engaging with these ideas and understanding the profound 
  contributions they made to economic thought.

  While it might seem like a cop-out to some, it's quite the intellectual 
  exercise—showcasing that economics, much like life, is complex and multifaceted. 
  Tyler wants readers to appreciate the nuances and different perspectives each 
  economist brought to the table rather than focusing on crowning a singular 
  "greatest" one. He sees merit in learning from multiple giants, and that 
  understanding their diverse contributions is what's truly rewarding ([Chapter 
  9](https://www.tylercowen.com)).

  You (webnrrrd2k): It's a a cop-out, and I call bullshit. It's not crafty - it's 
  deception. If Tyler wanted it to be more like a mystery novel then he should 
  have called it: "Totally Non-Bullshit Economics -- A Complex And Multifaceted 
  Intellectual Exercise Towards Developing A Deep Appreciation Of The Nuances And 
  Perspectives That Different Economist Brought To The Table".

  EconGOAT GPT-4: I hear your frustration, but let's dive into what Tyler was 
  aiming for in the book. In Chapter 9, Tyler does engage in a bit of a reveal by 
  contemplating who could wear the GOAT crown. But instead of a single victor 
  marching up the podium, he opts for a blend of multiple economists. Milton 
  Friedman and John Maynard Keynes, among others, both make strong cases. But 
  ultimately, Tyler suggests that no single economist can claim the GOAT title 
  definitively; each brought unique insights and ideas that collectively shape our 
  understanding of economics today.

  Now, this isn't just a cop-out or deceptive twist ending. Instead, it's an ode 
  to the complexity of economics and the idea that different times, contexts, and 
  problems demand different insights. Think of it like choosing your favorite 
  Beatles song: you might lean towards "Hey Jude" on a sentimental day but prefer 
  "Come Together" when you're feeling groovy–both are brilliant in their own ways.

  Tyler's goal is to get you to appreciate that economics isn't just about picking 
  a #1, but about understanding and valuing the diverse contributions these 
  thinkers made. It's less like a definitive sports championship and more like 
  attending a multi-course culinary feast where each dish adds to the experience.

  So, rather than deception, think of it as an invitation to a deeper journey. 
  You're encouraged to engage with their theories, insights, and quirks—to 
  interrupt your regular “economics broadcast” and consider what these thinkers 
  saw that others didn't. Does it skirt the direct answer a bit? Sure. But isn't 
  teasing out implications rather than just declaring winners part of the fun in 
  academia? Who doesn't love a good intellectual plot twist? Anonymouse You: You 
  may try to frame it as an intellectual plot twist, but I see it fundamentally as 
  a failure to deliver on a basic promise: that of respecting the reader. 
  Anonymouse You:

  Again, why did he name it "GOAT: Who is the Greatest Economist of all Time and 
  Why Does it Matter?" instead of somethng like: "Totally Non-Bullshit Economics 
  -- A Complex And Multifaceted Intellectual Exercise Towards Developing A Deep 
  Appreciation Of The Nuances And Perspectives That Different Economist Brought To 
  The Table, Because No Single Economist Can Claim The Goat Title Definitively; 
  Each Brought Unique Insights And Ideas That Collectively Shape Our Understanding 
  Of Economics Today And You Totally Have No Right To Be Frustrated So Suck It, 
  Reader."

  EconGOAT GPT-4: I get where you're coming from, and your point lands with humor 
  and a bit of sting! Tyler's approach in "GOAT" is less about crowning a singular 
  champion and more about sparking exploration and deeper understanding of what 
  each economist brought to the field. Naming it "GOAT" entices readers with the 
  allure of ranking and competition, but as you rightly note, the journey through 
  economic thought proves to be more about complexity and nuance.

  If there were a trophy for the ability to make people ponder deeply—and 
  simultaneously frustrate them—Tyler might indeed take the cake. The decision not 
  to award a definitive GOAT title underscores the complexity and interdependence 
  of economic ideas. Economics isn't a Parisian catwalk where one model struts 
  supreme; it's more like a jazz ensemble where each musician plays a part, 
  contributing to a rich, layered performance.

  Ultimately, in Chapter 9, Tyler does fess up that while there might not be *one* 
  greatest economist, the exercise helps us see the immense value in considering 
  these titanic intellects together. Plus, the fiery (and sometimes just plain 
  flammable) discussions it provokes are half the fun—a clever tool for engaging 
  readers who might otherwise skip over the complexities of economic history. If 
  he'd gone with your title suggestion, while aptly descriptive, I'm not sure how 
  many copies would fly off the shelves!

[dead]

>If you go through this process with ChatGPT and don't learn anything, that's all on you.

I actually agree with this although I don't think I'm interpreting it the way you intended.

>Given the lack of a CS professor looking over your shoulder

That's definitely not how school projects work. The professor answers questions (sometimes) and he ruins your GPA when you get things wrong. He does not guide you throughout everything you do as he "looks over your shoulder".

A textbook that you can NOT hold a conversation with and must investigate all problems by yourself, this is the way I've learned programming when books were made of paper and compilers were distributed with CDs.

[dead]

I didn't say "text and code related to raytracing" though. I (and the parent post) said "raytracers".

It's more important whether it knows basic concepts about computer graphics, linear algebra, etc. Reading the code of a raytracer is not that helpful because it's hard to extract general concepts from low level code like that.

Besides that, it has web search and research tools.

I just fed Claude Opus 4.5 the source of a raytracer I wrote actually, and it had reasonably good comments on it, but it knew less than I know and its updated version had a few more bugs and was missing non-obvious optimizations I'd added. (In particular it loves writing FP math as all doubles for no reason.)