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

I won't read LLM authored fiction

mccormick.cx

Post reply on HN
Print view View original

91–100 of 118 posts

Re: I won't read LLM authored fiction

#91

Post by theshrike79 »

Planktonne wrote: post #88
theshrike79 wrote: post #80

I think many people forget that the vast majority of books aren't high art. Your mind goes to Heinlein, Arthur C. Clarke, N.K. Jemsin, or Pratchett. My mind goes to Ice Planet Barbarians[0] or Crimson Worlds[1] (both written by actual humans, but I think they are good representations of their genres) There are so many books in the romantasy genre specifically that could be just mad libs templates for AI Generated boo…

You're underselling those books and overselling AI; people have tried generating romantasy and power fantasies, and it's very obvious that it's not up to par. People want tropes, sure, but that's not the same as wanting trash; our culture is built on satisfying narratives treading well-worn paths, and there's a skill to it. Pratchett, for example, was only able to do what he did because he was deliberately playing wi…

What's the difference between "trash" and "tropes" in your mind?

For example the good old Harlequin books were pretty much trash: https://en.wikipedia.org/wiki/Harlequin_Enterprises

But when the expectation is trash, they deliver. They're the Hallmark Movies of books. It's not Citizen Kane, but sometimes you just want a predictable plot of a big city girl coming back to her home town and falling in love with the rugged local man.

Re: I won't read LLM authored fiction

#92

Post by mxmlnkn »

km3r wrote: post #30

While I understand the hesitancy for LLM fiction, I do look forward to LLM powered games, *IF DONE RIGHT*. I imagine a game like Skyrim, where each character has handwritten backstory and dialogue, with an LLM extending that. Having the city guard dynamically react to what you do, stay in character, and even point you to new POI from those conversations seems like a very cool new dimension in storytelling. I took a c…

I have been imagining this since GPT-3. I still only know of very few games making use of LLMs. There are add-ons for Skyrim, and web search points me to NVIDIA's ACE autonomous game characters framework and games such as InZOI, PUBG's ACE-powered AI teammate, Dead Meat (unreleased interrogation game), AI Dungeon, Suck Up!, Vaudeville, and more. It seems there are a few more than I would have thought, but the smaller ones seem to have some mixed reviews. It would be interesting to check out how these games resolve the reasons against LLMs in games I can think of:

Cost: LLMs fitting into local GPUs, in addition to the memory required for game textures, are too constrained for the quality, latency, and concurrency required. Connecting to the cloud would be too expensive, and even if it would work, it would indeed be the death of local offline gaming, and it would give a valid reason for a subscription to keep the servers running as opposed to a buy-once play-forever game business model.

Unreliability: You don't want to miss a major quest because the LLM did not decide to hand it out. It might be workable with some proper "agentic harness", with some hardcoded world lore, long-term memories, goals, midterm memories, some deterministic actions, and a short-term free-form loop that gets cleared every now and then. For OpenClaw instances, it would be the SOUL.md, but it would have to be read-only. Some logic might have to be hardcoded outside of LLMs, e.g., to start a new narrative branch powered by a new character memory when a keyword has been mentioned or a quest item has been given. Similar to agentic frameworks, it would have tool calls such as `offer_quest`, `give_reward`, etc.

These ideas seem to converge onto the Westworld mechanics of backstories, cornerstone memories, reveries, narratives, and loops, at least as far as I remember them from the series. Thinking about it, given enough investment, I feel like the amusement park of Westworld should already be somewhat possible to implement with the recent advances in LLMs and robotics.

In the end, I am not sure how much sense it makes for games. Maybe it would suffice to only make companion characters LLM-enhanced while NPCs stay pre-programmed in order to let the game stay deterministic. Games should simplify real life in order to increase enjoyability. Making all characters backed by LLMs might decrease enjoyability because of forgetfulness or confabulations inconsistent with the game world and actions. It would need to be heavily constrained and trained or prompted to say "I don't know about that.". It might also be questionable how much needs to be dynamic. E.g., when thinking about the NPCs in The Witcher, which are talking about random stuff, maybe you only need to pregenerate much more random stuff for them to talk about so that you don't notice the repetition, but there might be no need to have this completely dynamic and burn through GPU power for every action. The question would be what to cache and what really needs to be dynamic.

Re: I won't read LLM authored fiction

#93

Post by duckmysick »

jalev wrote: post #15
lilerjee wrote: post #9

How to detect which fiction, article, or review is created by fake AI or LLM? There are too many texts generated by LLM on Internet now. The experience of exploring Internet is very bad now.

It's often quite easy, because most people who author articles with LLMs do not bother doing any kind of post editing. Meaning you can see/build a mental map of common tropes[^1] for what to look for. Once you read perhaps two or three articles authored with LLMs you will not be able to unsee it. [^1]: https://tropes.fyi/

For fun, I pasted a few Matt Levine's newsletters into the AI Vetter on the above page. Since it can't fetch the Bloomberg's paged directly, I had to copy the content into Github gists.

4 out of 5 were marked as suspicious, mostly citing short punching sentences, negative parallelism, and content duplication.

Re: I won't read LLM authored fiction

#94

Post by chr15m »

montebicyclelo wrote: post #25

worth noting you don't usually read _that_ many books in your lifetime. e.g. 20 a books a year for 40 years is just 800 books side note: i've noticed people writing with no caps, unusual grammar, splling mistakes, etc. which does differentiate their output from typical llm output - although ofc llms can probably imitate that

It's true and so it makes sense to be a bit picky about what you read. A great many non-fiction books should probably be blog posts or articles for example.

Re: I won't read LLM authored fiction

#95

Post by thunky »

j4yav wrote: post #86
unparagoned wrote: post #81

Earlier quoted context omitted.

But your view of art is based on who you “think” made it. So if someone lies about who made the art your views on the art changed. That’s a strange position that doesn’t make sense to me.

Context can very easily enrich or ruin nearly anything, but especially creative expression. I'm surprised this is seen as strange.

A Million Little Pieces was a popular book about addiction that inspired a lot of people. Turned out the story wasn't true, and so a lot of inspiration turned into anger.

Always thought that was interesting, because if the lies weren't exposed the readers would have remained inspired.

https://en.wikipedia.org/wiki/A_Million_Little_Pieces

Re: I won't read LLM authored fiction

#96

Post by cognitiveinline »

Planktonne wrote: post #64
darkwater wrote: post #41

Earlier quoted context omitted.

True, but that does not mean that the average teacher won't grade you badly if your interpretation is completely opposed to their and what was discussed during lessons.

There are bad teachers, sure. There are also bad students who think that the issue was that they weren't being taught when it was actually that they weren't trying to learn.

Bad teachers are the default, and good ones exception, maybe 10:1. It's an underpaid, overworked job mostly.

Re: I won't read LLM authored fiction

#97

Post by j4yav »

thunky wrote: post #95
j4yav wrote: post #86

Earlier quoted context omitted.

Context can very easily enrich or ruin nearly anything, but especially creative expression. I'm surprised this is seen as strange.

A Million Little Pieces was a popular book about addiction that inspired a lot of people. Turned out the story wasn't true, and so a lot of inspiration turned into anger. Always thought that was interesting, because if the lies weren't exposed the readers would have remained inspired. https://en.wikipedia.org/wiki/A_Million_Little_Pieces

One time I called in sick to work, they even sent me flowers. Later they found out I was lying and wasn't really sick and they got angry about it. Humans are strange.

Re: I won't read LLM authored fiction

#98

Post by ghtbircshotbe »

unparagoned wrote: post #81
imathew wrote: post #29

I won't (if I know) either, but for me it's because a very big part of reading fiction or enjoying any art is that you have a relationship of a kind with its creator. When a passage surprises me or a song lifts me or a painting inspires me it's partly because I'm amazed that someone was able to do that, and that they were able to reach me like that. Everyone borrows or steals from prior art but I'm still amazed by th…

But your view of art is based on who you “think” made it. So if someone lies about who made the art your views on the art changed. That’s a strange position that doesn’t make sense to me.

It seems like a pretty normal behavior. Just look at the whole tabloid industry that follows actors and musicians around. You might like bland architectural paintings, but knowing they were made by Hitler sort of changes your impression.

Re: I won't read LLM authored fiction

#99

Post by cognitiveinline »

Devasta wrote: post #12

English teachers around the world have loathed that "The curtains were blue" meme, and are absolutely right to do so, but what happens when you ask what an author meant by the blue curtains and the answer is a fairly definitive "it's just the probabilistic output of the model the author used, it doesn't mean anything"? Sure some people are just piggies lining up at the trough to consume content like it's the custard…

I think it's unhealthy, your attitude.

When you have such disdain for "piggies", and hold your opinion as the true one, on a very subjetive question, well, it's very pitiable.

Re: I won't read LLM authored fiction

#100

Post by ghtbircshotbe »

sdoering wrote: post #83
dgellow wrote: post #16

Earlier quoted context omitted.

> What does the author wanted to tell us with this story." Because -> The author never wrote that down. And deriving their intentions from a fictional text felt just like making shit up It’s an exercise in engaging intellectually with the work. It’s not about knowing for a fact what the author wanted to communicate. Art is about engaging with human emotions and thoughts, not about deriving specific facts.

> Art is about engaging with human emotions and thoughts Exactly. Still, that does actually not contradict what I wrote. You can still do this from a viewpoint of Structuralism, Formalism, Reader Centric Schools of Interpretation and Author Centric Schools of Interpretation. Non of those are less intellectually" engaging with the work. Differently - and in my personal opinion more or less intellectually rewarding - y…

It's not just the reader engaging in the work, but the author. If the author can't or is unwilling to put in any actual work, and also lies about it, I've lost all respect and interest in them. Saying you only care about the message and not the messenger is sort of like saying you only care about the words coming out of your friend's mouth but not your friend.
Post reply on HN