Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I avoid using LLMs as a publisher and writer

lifehacky.net

Post reply on HN
Print view View original

131–140 of 141 posts

Re: I avoid using LLMs as a publisher and writer

#131

Post by tombarys »

esjeon wrote: post #70
tombarys wrote: post #2

I am a book publisher & I love technology. It can empower people. I have been using LLM chatbots since they became widely available. I regularly test machine translation at our publishing house in collaboration with our translators. I have just completed two courses in artificial intelligence and machine learning at my alma mater, Masaryk University, and I am training my own experimental models (for predicting bestse…

I know a publisher who translates books (English to Korean). He works alone these days. Using GPT, he can produce a decent-quality first draft within a day or two. His later steps are also vastly accelerated because GPT reliably catches typos and grammar errors. It doesn't take more than a month to translate and print a book from scratch. Marvelous. But I still don't like that the same model struggles w/ my projects.…

This is a topic for another article! We tried hard to use (test) translation tools in some real-life scenarios. The results seemed like they can help first but then we spent a lot of time again to reach our standards. As a side-effect, our translators and editors felt they are losing their own creativity and sensitivity in that process.

We are a publisher which succeeded due to the highest-quality translations. Our readers appreciated it and ask for it. Czech language is very rich and these machines are not able to make the most of it. The non-fiction sphere needs a lot of fact-checking e.g. in local and field terminology too. So even we can imagine the process of translation could be technically shortened by machine translation, it would probably ruin our reputation in a long term.

At least for now...

Re: I avoid using LLMs as a publisher and writer

#132

Post by tombarys »

magic_hamster wrote: post #105

There have been quite a few skeptic blog posts recently about LLM. Some say they won't use it for coding, others for getting creative ideas, and others won't use it for editing and publishing. However, the silent issue all these posts have in common is that resistance is futile. To be fair, I also don't like using Copilot when working on code. In many cases it turns into a weird experience when the agent generates th…

I understand. The question is what does it mean to "survive" for someone.

For me survival means: - continuing to do my best at the language level – even if more people would start be gradually satisfied with less - I just believe that education, critical thinking and evidence-based principles are at core of humanity progress and one day it will make comeback - I am ok with smaller income and not wishing to exchange it for creating bullshit

The adaptation for me means: - generally: stay open-minded - I have to understand and somehow accept that the prospect is a bit grim but not to fall into some extreme and doom thinking - I have to explore new ways how to augment human-oriented creativity (with or without these tools)

What do you think?

Re: I avoid using LLMs as a publisher and writer

#133

Post by tombarys »

shakna wrote: post #62
kelvinjps10 wrote: post #52

What about grammar and spelling corrections?

Not the author, but another author here and... Well, it has a problem with my use of the Oxford comma, for one. Because a huge amount of the corpus is American English, and mine ain't. So it fails on grammar repeatedly. And if you introduce any words of your own, it will sometimes randomly correct them to something else, and randomly correct other words to the made up ones. And it can't always tell when it's made suc…

Agree 100%.

Re: I avoid using LLMs as a publisher and writer

#134

Post by tombarys »

johnnyfived wrote: post #72

What's interesting about thinking of code as art is that there rarely a variety of ways of implementing logic that's all optimal. So if you decide on the implementation and have a LLM code it, you likely won't need to make major changes given the right guidelines (I just mean like a single script, for the sake of comparison). Writing is entirely different, and for some reason, generic writing even when polished (Chat…

> "Images can blend in the background, reading takes active processing so we're much more sensitive. And for the end user of a product, they care 0 or next to 0 about AI code."

Very interesting point!

Re: I avoid using LLMs as a publisher and writer

#135

Post by threatripper »

Arainach wrote: post #101
threatripper wrote: post #19

Earlier quoted context omitted.

You sound bitter. Did you try using more AI for the bug fixing? It gets better and better.

One of the biggest problems with AI is that it doesn't get better and better. It makes the same mistakes over and over instead of learning like a junior eng would. AI is like the absolute worst outsourced devs I've ever worked with - enthusiastically saying "yes I can do that" to everything and then delivering absolute garbage that takes me longer to fix/convince them to do right than it would have taken for me to ju…

Current models have no memory, they don't learn. You have to learn for them for now. You have to put the learnings in the instructions and in code comments. If you don't describe WHAT your code SHOULD do and WHY you write it in THAT particular way it will have no idea and the code may just look like bad non-standard code waiting to be "improved".

It works best if you keep close to mainstream styles and if you keep it easy and straight-forward.

Re: I avoid using LLMs as a publisher and writer

#136

Post by dvfjsdhgfv »

> in a programming environment, you can immediately verify the answer by evaluating the code (at least for code snippets).

Well, it's a trap. You see a snippet is right, you accept it. Next time you do it faster, and faster. And then you get one that seems right but it's not. If you're lucky, it will cause an error.

Re: I avoid using LLMs as a publisher and writer

#137

Post by tolerance »

tombarys wrote: post #130
tolerance wrote: post #9

For things like coding LLMs are useful and DEVONThink's recent AI integrations allow me to use local models as something like an encyclopedia or thesaurus to summarize unfamiliar blocks of text. At best I use it like scratch paper. I formed the habit of exporting entire chats to Markdown and found them useless. Whatever I found of useful from a given response either sparked a superseding thought of my own or was just…

You are right. It plateaued and even degraded in some way. Or we just got more sensitive to its bullshiting?

A little bit of both, I think. And I suspect that we aren't going to see another noticeable leap forward until specialized models become commonplace and/or people figure out exactly how LLMs productively fit their interests.

Re: I avoid using LLMs as a publisher and writer

#138

Post by southernplaces7 »

billy99k wrote: post #97
abenga wrote: post #96

Earlier quoted context omitted.

We care. If I get a video recommendation on YouTube and it is AI-created, I blacklist the channel. I will never listen to AI music. Even articles, the only way I will keep reading someone's writing is if I never find out they don't use it. I consume media and art to commune with my fellow man, not to look at pretty bitmaps and read just strings of prose.

You are not the average consumer.

[dead]

Re: I avoid using LLMs as a publisher and writer

#139

Post by mwigdahl »

andersmurphy wrote: post #95
mwigdahl wrote: post #86

Earlier quoted context omitted.

Yes, and it was exactly the same with compilers. All hype and fad -- everyone who's serious about software development writes in assembly.

It's false comparison compilers are deterministic. The only probabilistic behavior I've seen has been for performance (query planning/branch prediction). I mean you're not wrong the serious people drop into assembly when they need too. Even if you work in a context where you can't or don't drop down into assembly being able to make your own compilers is incredibly useful.

Sure, compilers are deterministic and LLMs are not. If you're asserting that a probabilistic process can't get you to a deterministic outcome, Monte Carlo integration would like to have a word.

My point was that comparing the rise of AI tooling to the rise of HLL compilers is a much better comparison than comparing it to crypto.

HLL compilers were originally seen as crutches and inferior tools and that "real" programmers used assembly. Compiler-generated code was derided as inefficient and ugly.

And it was! In the early days, a good programmer who knew the machine could outdo the compiler. But that didn't stop a huge expansion of new programmers who could write COBOL and FORTRAN but never learned assembly. And the compilers got better over time. These days it's a rare wizard who can outdo a compiler's optimizations, and it takes multiple orders of magnitude longer for those rare humans to achieve it.

LLM tooling isn't going away. Even in these very early days, it enables non-programmers to construct basic applications that work, using English requests! And the tools have gotten better on almost a monthly basis.

You can like them or not like them, just like the early programmers could like or not like compilers. But dismissing them as analogous to empty crypto hype is a bad comparison.

Re: I avoid using LLMs as a publisher and writer

#140

Post by andersmurphy »

mwigdahl wrote: post #139
andersmurphy wrote: post #95

Earlier quoted context omitted.

It's false comparison compilers are deterministic. The only probabilistic behavior I've seen has been for performance (query planning/branch prediction). I mean you're not wrong the serious people drop into assembly when they need too. Even if you work in a context where you can't or don't drop down into assembly being able to make your own compilers is incredibly useful.

Sure, compilers are deterministic and LLMs are not. If you're asserting that a probabilistic process can't get you to a deterministic outcome, Monte Carlo integration would like to have a word. My point was that comparing the rise of AI tooling to the rise of HLL compilers is a much better comparison than comparing it to crypto. HLL compilers were originally seen as crutches and inferior tools and that "real" program…

My comparison wasn't about the tech. It was about the proponents of said tech. A lot of people who push AI use the same sorts of arguments that people used to push crypto.
Post reply on HN