I feel 100% identified with you. I am working on a non ficton book about a niche topic and I wouldn't do it for the money at all. It's about the "prestige (or perceived prestige)". I am about to finish the first 1/3 of the book (the first draft, anyway), and I am already attempting to reach out to publishers to see if they would be interested in the book (at least the ones that don't require a literary agent!).

Some of them already replied saying the proposal seems interesting but they want to read a few chapters. I don't know if I am in the right path or not, but I'd love to read more about your experience and what can be shared!

Did you also write "Inspire!: Inspiration for Life and Life at Work" ?

Goodreads seems to think so. https://www.goodreads.com/author/show/14291276.Joel_Burke

What’s the name of your book? That sounds super interesting

Interesting handle (atlasunshrugged) - a reference to Atlas getting back to work rather than shrugging? (I know it's a book title.)

Is Estonia a good country to immigrate to for an American?

Where is the part where they forced a pivot? They asked for AI. He said no.

Do they have to return the Advance in this case? Is there any case where it makes sense fo reject the Advance?

Are you a bot?

There's a reason that ORA have huge credibility in technical publishing, and have for decades: a reliably good product.

Did they let you choose the animal to appear on the cover?

I heard the other day that LLMs won't replace writers, just mediocre writing.

On the one hand, I can see the point- you'll never get chatgpt to come up with something on par with the venerable Crafting Interpreters.

On the other hand, that means that all the hard-won lessons from writing poorly and improving with practice will be eliminated for most. When a computer can do something better than you right now, why bother trying to get better on your own? You never know if you'll end up surpassing it or not. Much easier to just put out mediocre crap and move on.

Which, I think, means that we will see fewer and fewer masters of crafts as more people are content with drudgery.

After all, it is cheaper and generally healthier and tastier to cook at home, yet for many people fast food or ordering out is a daily thing.

100% right. I buy lots of Japanese cookbooks secondhand. I found an Okinawa cook book for $8. When I received it, it was clear the author was just a content farmer pumping out various recipe books with copied online recipes. Once I looked up their name I saw hundreds of books across cooking baking etc. there was no way they even tried all of the recipes.

So yes, review and “narrative voice” will be more valuable than ever.

Agreed. Still amazed that people keep trusting the service that has like a 60% failure rate, who would want to buy something that fails over half the time?

Shame OP stopped their book, it would definitely have found an audience easily. I know many programmers that love these styles of books.

In my dream world, you take that book plus information about yourself (how good of a programmer you already are), feed that into AI and get a customized version that is much better for you. Possibly shorter. Skips boring stuff you know. And slows down for stuff you have never been exposed to. Everyone wins.

> There's just no way in hell ChatGPT at its current level is going to guide you flawlessly through all of that if you start with a simple "I want to build a raytracer" prompt!

This is the entire crux of your argument. If it's false, then everything else you wrote is wrong - because all that the consumer of the book cares about is the quality of the output.

I'd be pretty surprised if you couldn't get a tutorial exactly as good as you want, if you're willing to make a prompt that's a bit better than just "I want to build a ray tracer" prompt. I'd be even more surprised if LLMs won't be able to do this in 6 months. And that's not even considering the benefits of using an LLM (something unclear in the tutorial? Ask and it's answered).

Why buy the book when big AI can add it to their training data. Multitudes of people can then enjoy slightly higher quality output without you being compensated a single cent.

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.

Absolutely. And further because when you prompt ChatGPT as you write your ray tracer you don't know what the important things to ask are. Sure, you can get their with enough prompts of "what should I be asking you" or "explain to me the basics" of so and so. But the point of the book is all of that work has already been done for you in a vetted way.

You’re hitting at the core problem. Experts have done the intensive research to create guides on the Internet which ChatGPT is trained on. For example, car repairs. ChatGPT can guide you through a lot of issues. But who is going to take the time to seriously investigate and research a brand new issue in a brand new model of car? An expert. Not an AI model. And as many delegate thinking to AI models, we end up with fewer experts.

ChatGPT is not an expert, it’s just statistically likely to regurgitate something very similar to what existing experts (or maybe amateurs or frauds!) have already said online. It’s not creating any information for itself.

So if we end up with fewer people willing to do the hard work of creating the underlying expert information these AI models are so generously trained on, we see stagnation in progress.

So encouraging people to write books and do real investigative research, digging for the truth, is even more important than ever. A chatbot’s value proposition is repackaging that truth in a way you can understand, surfacing it when you might not have found it. Without people researching the truth, that already fragile foundation crumbles.

> Isn't it obvious? Because the ChatGPT output wouldn't be reviewed!

Reviewed by a human. It's trivial to take the output from one LLM and have another LLM review it.

Also, often mediocrity is enough, especially if it is cheap.

This discussion might be a bit more grounded if we were to discuss a concrete LLM response. Seems pretty freaking good to me:

https://chatgpt.com/share/6955a171-e7a4-8012-bd78-9848087058...

I wouldn’t be surprised if publishers today delegated some of the reviewing to LLMs.

> There's just no way in hell ChatGPT at its current level is going to guide you flawlessly through all of that if you start with a simple "I want to build a raytracer" prompt!

I mean, maybe not "flawlessly", and not in a single prompt, but it absolutely can.

I've gone deep in several areas, essentially consuming around a book's worth of content from ChatGPT over the course of several days, each day consisting of about 20 prompts and replies. It's an astonishingly effective way to learn, because you get to ask it to go simpler when you're confused and explain more, in whatever mode you want (i.e. focus on the math, focus on the geometry, focus on the code, focus on the intuition). And then whenever you feel like you've "got" the current stage, ask it what to move onto next, and if there are choices.

This isn't going to work for cutting-edge stuff that you need a PhD advisor to guide you through. But for most stuff up to about a master's-degree level where there's a pretty "established" progression of things and enough examples in its training data (which ray-tracing will have plenty of), it's phenomenal.

If you haven't tried it, you may be very surprised. Does it make mistakes? Yes, occasionally. Do human-authored books also make mistakes? Yes, and often probably at about the same rate. But you're stuck adapting yourself to their organization and style and content, whereas with ChatGPT it adapts its teaching and explanations and content to you and your needs.

Does this type of ray tracing book exist? It’s something never learned about and would love to know what courses or books others have found valuable

There's just no way in hell ChatGPT at its current level is going to guide you flawlessly through all of that if you start with a simple "I want to build a raytracer" prompt!

Have you tried? Lately? I'd be amazed if the higher-end models didn't do just that. Ray-tracing projects and books on 3D graphics in general are both very well-represented in any large training set.

> a professional, who has taken the time to divide it up into easily digestible chunks which form a coherent narrative, with runnable intermediate stages in-between.

Tangentially related, but I think the way to get to this is to build a "learner model" that LLMs could build and update through frequent integrated testing during instruction.

One thing that books can't do is go back and forth with you, having you demonstrate understanding before moving on, or noticing when you forget something you've already learned. That's what tutors do. The best books can do is put exercises at the end of a chapter, and pitch the next chapter at someone who can complete those exercises successfully. An LLM could drop a single-question quiz in as soon as you ask a weird question that doesn't jibe with the model, and fall back into review if you blow it.

> Because the ChatGPT output wouldn't be reviewed!

So what? If it's not already, frontier LLM one-shot output will be as good as heavily edited human output soon.

Technical books don't sell well to begin with. I've written a couple w/ a major publisher, it never paid back the RAM I needed to purchase to run the lab environment.

Publishers are going to demand chasing the hot-new-thing which will most likely be irrelevant by the time the book is on the shelf.

"How to write x86 ASM... with the Copilot Desktop app! - Build your bootloader in 15 seconds!"

The article hints at this, but publishers live on the outsize success of very few of their books, and the rest of them are losses.

It's exactly the sort of financial pressure that will make them chase fads and trends, and it gets worse in difficult economic times.

You won't believe how bad things are where I live. We have a government-subsidized AI image generation course here.

Industry-wide? Looks damn near pan-industry to me

I’ve never worked in technical publishing but I have a few acquaintances who do. Adding chapters on AI is pretty close to industry wide for new writers. Experienced writers with sales figures have a lot more freedom.

The thing is, it’s not about getting chapters published on AI. The publishers are keenly aware that AI is using their content to steal their market and so anything they publish on AI will be obsolete before the final manuscript is published. It’s about getting potentially difficult first time authors to quit before their first third gets approved - that’s when the author is owed their first advance.

It’s a lot easier to slaughter sheep if the most docile select themselves.

I came away with the same impression. I was less blaming the publisher and more about life getting in the way with the author

Agreed. The one time I worked through a publisher I beat every schedule and it was all smooth enough.

I’m glad I did it but I’m not sure how much the publisher added beyond some prestige and a few bucks. The first edition in particular I felt I needed to pad out a bit to meet length requirements.

Manning makes sense - all the details fit, and there aren't that many. Publishing is a stupid business that makes less and less sense every passing day. Self publishing and going through an outlet, marketing for yourself, or contracting out the relevant tasks, will save you a ton of money for anything publishers can offer anymore. They survive more and more often on grift and network effects that are increasingly irrelevant and often run counter to the interests of a given author or work.

Glad the author got out relatively unscathed.

Self publish - especially with AI available to get you through the stuff where you just need superficial or process knowledge, like which firms to hire and how to market a self-published work, what boilerplate legal protections you need. You'll get 99% of the value of a big publishing firm at a small fraction of the cost, and you won't have to put up with someone else taking a cut just because they know a few things that they don't want to tell you in order to justify taking your money.

I’ll also note that the publisher was right to bring up AI, even if they did not do it in an artful way. He himself comes to doubt the need for his book in the era of LLMs and he says that is part of why he cancelled. To his publisher’s credit they raised the issue early in the process where a pivot would have been more practical.

In fairness to the author, he presents a reasonably balanced view and it did not read to me like “my publisher sucked.”

Every writing group has that person the keeps restarting their project, or abandoning a project when it gets hard, to start another one with another 'great' idea.

The upshot is, they don't want to do the hard part - continuity editing, developmental editing, hell, just finishing the dang thing. Even the boring chapters you didn't really have any idea what was going to go on there.

Writing, as an occupation, is a whole lotta schmoozing, attending conferences, volunteering, promoting. Maybe 1 month of writing a year, for 11 months of the hard stuff.

I have a buddy who says he always wanted to start a bar. I said, You like budgeting? Taxes? Hiring? Firing? Stocking? Remodeling? Promoting?

Nah; turns out, he just likes to hang out in bars.

The only reason you start a business is, because you like to run a business.

The only reason you become a writer is, because you like the business of writing.

there was a funny joke that chatgpt removes the critical part of being a writer which is hours staring at a blank screen, then deleting everything you've done on a weekly basis.

> I've come to hate every cookbook that starts with 100 pages of here is a tour of my pantry, which sounds a lot like, here is how to use pip!

Yeah I agree. I hate when books do more hand holding than the reader clearly needs to the point of tedium. Plus many of those setup steps like how to use a package manager change over time and make the book stale instead of evergreen. And Austin was clearly not writing an absolute beginners book.

That's why when I pitched both the Classic Computer Science Problems series and Computer Science from Scratch I explicitly told publishers in the proposals that I was not writing a beginners book (been there, done that). I was clear that I was writing an intermediate book for people that already know programming.

It's a different, more narrow audience. But you can be successful if you write a good book. It's also a less tapped market and luckily publishers were able to see that.

Just skip the chapter?

Honestly, I wouldn't consider publishing a book if it didn't have that information. There's no reason to give up half or more of the potential market for a book because it's arbitrarily pitched at advanced users. Assuming the customer knows how to use pip would be crazy.

> I've come to hate every cookbook that starts with 100 pages of here is a tour of my pantry

To each their own. As someone who learned to cook as an adult, I’ve appreciated seeing both what someone has and what nonsense I own that they manage just fine without.

I've also authored multiple technical books and had the exact same reaction.

While writing I have had similar feeling as the author to publisher/editor comments, especially related to:

> The unhelpful feedback was a consistent push to dumb down the book (which I don't think is particularly complex but I do like to leave things for the reader to try) to appease a broader audience and to mellow out my personal voice.

I also remember being very frustrated at times with the editor needing things "dumbed down". I used to get very annoyed and think "didn't you pay attention! We covered that!" But then I realized: If I can make this easy to understand by a fairly non-technical editor at a first pass, it absolutely will make this book better for the reader.

Publishers have a lot of experience publishing books, so I've learned that their advice is often not bad.

There was also plenty of advice from the editors I vehemently didn't agree with, so I pushed back and quickly realized: publishers need you more than you need them, so very often you do get final say.

But you still have to actually write the book. Book writing is hard, and a much more complex process than writing blog posts. Personally I feel all the editorial feedback I've gotten over the years has made not only my books better, but also has really pushed my writing to be higher quality.

That's how I read this too. The publisher invested a non-trivial amount of work and was left with nothing, for no better reason than the author changed their mind. From the tone of the post, the author seems to not realize or care.

It does feel high pressure in the moment, but I wouldn't have two published technical books if not for the consistency and push of my editors and the publisher.

Another constraint of a technical book that I didn't see mentioned here was that time almost has to be very limited during the writing process. I worked on a couple mobile development/design books, and an iOS 18 programming and design guide is worthless after Apple announced Liquid Glass last summer. At 2+ years into the project and seemingly only 1/3rd complete, the publisher really needs to be sure the content will still be relevant after released.

Yeah, I mean I hate to seem churlish about this, but I really didn't read this with sympathy for the (would-be) author.

> the author didn’t make time to write the book and then lost interest

That was my read as well. The book deal fell apart because the author never wrote most of the book.

If the author of this article just finished the book the publisher would have just published it without much fuss and probably without any significant changes.

The author had all the leverage regarding content. It’s not like the publisher could actually incorporate what they were asking for with AI, they still need an author to do that and it was a totally new subject at the time. Their demands were empty.

I don’t think the author would have finished the book if it was self-published. They clearly didn’t want to write a book that badly.

Not to say that finishing a whole-ass book is easy, I’m certainly not going to pretend that’s the case.

I’ve lately been trying to finish more side project type things in my life because these dead ends themselves feel empty to me. I am trying to set scope reasonably and then just finish even if it’s painful or there’s no confetti-style payout and nobody else cares.

They never got the advance because they didn't get to the first milestone.

When you have original information that hasn't been released anywhere else in the world, why would a book be a bad choice?

> Though I guess people would argue you can just ask a LLM now instead of reading my book.

I would certainly not argue that. LLMs do not understand anything, and are thus prone to non-deterministic inaccuracies in their output. Due to that, I think it is extremely foolish to use one for learning unfamiliar topics. Give me a book every time, because (if it's a good book) I am guaranteed to actually learn something. Not so with LLMs.

I think I could ask an LLM to explain linear algebra. I think it would be less good at the 'here are some things you should know' aspect. One reason for this is that people might not ask, but the LLM might not agree with your list anyway.

I think there is still a place for a book here. I think I might buy a book (or may have done 10 years ago when I was still coding) of things you should know (especially from a respected publisher), that being a longer form book I could work through over time.

that'll only be the case if you actually write the book so that the LLMs have that info. Until then they can't regurgitate your know-how.

Why should I know linear algebra, ooc?

Udemy and Coursera both have Math for Machine Learning courses that start with Linear Algebra. Then, Calculus and Probability and Statistics. They're often $25-50.

You might want to look at their outlines to see what they're teaching. Then, decide if you can do something similar and/or cheaper.

For most books, but technical non-fiction in particular, the payout isn't nearly worth enough for the effort.

And by "most" there I mean "all". Yes, there are exceptions, but those exceptions prove the rule.

I've written 2 technical books, for incredibly niche audiences, where the total number of potential buyers is numbered in the low thousands.

I self published as a PDF. and charge $200 a copy, of which I keep $200. It's -marginally- worth it. But the hourly rate is much lower than my day job.

The marketing benefit (as it affects my actual business in the same field) is likely real, but hard to measure. Still, having "written the book" opens doors, and brings credibility.

You have to many me to engage with Amazon. I will not spend a penny of my personal income to enrich the deplorable Jeff Bezos.

Amazon and companies like them must be broken up because they harm the producers and consumers with dictating buying and selling pricinf.

Care to share links to your books?

No, their incentive is to wait and see what books are taking off, then pile on the money when they know it's already a winner. Today, unproven authors are expected to do their own marketing.

> This is why most publishers won't even talk to you unless you have a finished manuscript already

This is absolutely not true in the world of technical publishing. I mean books published with publishers like O'Reilly, Manning, No Starch, etc. Usually you come to them with just a proposal and a couple chapters or even just a proposal. Or their acquisition editors actually reach out to you. It's the exception (not quite rare, but definitely less than 20% of books) that comes to them with a finished manuscript. I did that with my last book. I've published 5 technical books across three different technical publishers, so I know a bit about this business...

I'm just replying to this comment to not discourage people who just have an idea and not a finished book yet but have the motivation to finish and want to get a deal.

This is not true for business books like mine. It's vital to write a proposal first in that world; publishers want to influence the content (as in the OP article).

I think the same is true for tech books but I don't know as I haven't written one.

A novel or other fiction is the opposite; there you do have to write the whole thing first.

> Sounds like your publisher was trying to just take your work and sell it. Giving you the least amount you’ll agree to.

That’s literally what a publisher does.

The first half of the advance was to be paid after the first third was approved.

They never got to that point.

I don't think he ever got the first half of the advance...cherry-picking from the TFA:

> They offered a $5000 advance with the first half paid out when they approve of the first third of the book and the second half when they accept the final manuscript for publication.

> I continued to get further behind on delivering my revised draft of the first 1/3.

> Around this time, there was a possibility of me changing jobs. Oh, and my wedding was coming up. That was the final nail in the coffin.

> There were too many things going on and I didn't enjoy working on the book anymore, so what is the point? I made up my mind to ask to freeze the project.

> They agreed.

I'm on it!

The 500 - 5000 figure, which is correct, is why most folks should instead self publish via KDP. 70% royalties mean you can get 10-50k easily with an average book. If the book is a success, you can switch career to a full time author if you wish. All this with full creative freedom. Many years ago, I canceled my Redis book for a large publisher for similar reasons to the OP: too many "do it this way" requests.

> I am honestly a bit puzzled by this description and I wish they had named the publisher.

Does it matter which exact one if all the publisher oligarchs behave exactly the same?

This is absolutely true, speaking as someone who has both self-published and also published with a big publisher. Each choice has pros and cons.

In my case, I self-published and sold a book for several years, and then published an updated version with O'Reilly.

I decided to do that because I came to realize people judge self-publish books as less vetted and lower quality.

That may be often true. But in many cases, a self-published book can be much better than those released by a former publisher. I certainly believe it was true in my case.

But in the end, I decided my highest best opportunity was to go with a well-regarded publisher, for the authority that would bring.

And it changed things. People treat me differently now, like they consider me more of an authority. Even though it's essentially the same book; it just has an O'Reilly logo on the cover now.

Whether that should be the case is up for debate...

But it absolutely made people listen more seriously to my message. and I believe it has massively increased the positive impact of that book on the world.

Financially, I think it's been about even. For me it was worth the tradeoff for other reasons, but I don't think that is always the case for every author and every book.

In the era of AI, who is going to buy books?

You are reading a lot of things that I didn't say.

The publisher didn't do anything "wrong". It was their suggestion to freeze it instead of cancel immediately. I didn't intend on giving up on the book even then. I didn't return the advance because I never received the advance.

It says the first half of the advance would be paid on approval of the first third of the book. It also says that the first third of the book was never submitted. So I don't think the advance was ever paid out.