Comment by layer8

1 day ago

It would actually be nice to have a book-LLM. That is, an LLM that embodies a single (human-written) book, like an interactive book. With a regular book, you can get stuck when the author didn’t think of some possible stumbling block, or thinks along slightly differently lines than the reader. An LLM could fill in the gaps, and elaborate on details when needed.

Of course, nowadays you can ask an LLM separately. But that isn’t the same as if it were an integrated feature, focused on (and limited to) the specific book.

6 comments

layer8

vunderba 1 day ago

I've not used it, but isn't this kind of what NotebookLM does?

You drag a source into it such as a books PDF and then you have a discussion with it.

https://notebooklm.google

layer8 1 day ago
What I’m imagining is an LLM that is strongly tied to the book, in the sense of being RLHF’d for the book (or something along those lines), like an author able to cater to any reader interested in the book, but also confined to what the book is about. An LLM embodiment and generalization of the book. Not an LLM you can talk about anything where you just happen to talk about some random book now. The LLM should be clearly specific to the book. LLMs for different books would feel as distinct from each other as the books do, and you couldn’t prompt-engineer the LLM to go out of the context the book.
- p1esk 21 hours ago
  
  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?

jchallis 1 day ago

Tyler Cowen's GOAT book explores this in depth. Try it out! https://goatgreatesteconomistofalltime.ai/en

johnnyfived 1 day ago

Genuinely have no idea what the novelty of this is for versus just uploading a PDF to ChatGPT. In terms of UX it is incredibly limited for a book evolution work.

webnrrd2k 20 hours ago

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!