This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.
Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.
We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:
-
Shaming.
-
Attempting to 'build consensus' or enforce ideological conformity.
-
Making sweeping generalizations to vilify a group you dislike.
-
Recruiting for a cause.
-
Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.
In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:
-
Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.
-
Be as precise and charitable as you can. Don't paraphrase unflatteringly.
-
Don't imply that someone said something they did not say, even if you think it follows from what they said.
-
Write like everyone is reading and you want them to be included in the discussion.
On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.
Jump in the discussion.
No email address required.
Notes -
Art is meh, writing style is terrible. Part of this is the lack of RLVR; the alternative just trains the model to produce the lowest common denominator, which is what we get.
But, fundamentally, I don't think the labs care about art or prose style. Writing can be slop and it'll annoy people for a couple years, while math is a load-bearing component of RSI. Get RSI, and you can catch up on writing over a long weekend.
That is probably true, but not really indicative that things will improve. The labs do care about programming, and LLMs still suck at programming. So even the thing the labs have put probably the most effort into, the machine is still below the level of a competent human.
More options
Context Copy link
I think these are categorically different than math: the theorem prover languages are at least a clear Boolean success criterion. "Is this painting/book good?" is canonically an opinion question without a singular answer.
From what I can tell, human-driven post-training has historically been done with English speakers hireable at low hourly rates, but probably not ones that appreciate Ulysses (I certainly haven't read it). Even if they could afford English department grad students, would they be willing to train, effectively, their replacements? How do you rank the writing styles of Faulkner versus Hemingway? It seems there is at least some room for legitimate creativity there.
Artistic style isn't just a matter of opinion, it's a matter of opinion in a specific context.
I swear the above sentence was an accident, and I only noticed what I was doing halfway through, but it'll work perfectly as a demonstration too. Aren't you sick of that "It's not X, it's Y" idiom right now? Judicious use of thesis/antithesis pairs was compelling back in the Before Times of 5 years ago, but because it was compelling RLHF seized upon it as Good Writing, and so now AI writing uses it everywhere and we're sick of it. Not that you loved Caesar less, but that you loved Rome more? Learn to write for yourself, Will, you hack!
Great art is supposed to have a timeless quality too, but a lot of good art is directly speaking to the wider artistic milieu of its time, and making choices about what styles and tropes can be used unashamedly vs what have become cliches that must be avoided or subverted. This is normally a stable system, because as something becomes briefly overused it immediately begins to repel other potential users, but if a huge swath of humanity is using the same handful of systems that are trained on the same total-corpus-of-human-art then we lose a lot of that stabilizing negative feedback, and the results we get stuck with are hard to avoid via simple instruction alone.
More options
Context Copy link
More options
Context Copy link
I think this is just a technical problem, frankly. You can prompt models to actually have decent writing style with enough effort which means it's possible that fine tuning or some even simpler operation on the output fixes the problem entirely. And that's a valuable product so i'm certain someone's going to come up with it eventually.
Slop writing and em dashes is the record skipping of our time, nothing more. People will miss it and try to ape it in 20 years.
People keep saying this but never share the prompts. It's not possible.
What?
Maybe this is down to the fact that there's a high variance in what people consider to be "decent writing style", but you can just falsify that style isn't controllable by asking your favorite SotA model to write in the style of your favorite author. Never mind by using a fine tuned model.
Now if what you consider necessary for "decent" isn't quantifiable or is outside of the abilities of the current methods, fair enough, but I sure would like to know what it actually is.
That paper doesn't do it
It's a review of a whole area of research trying to do it with various levels of success. Fine tuning is still the best way of altering style AFAIK, but all this is insofar as we mean the same thing by "it". But it seems clearly we don't. So what is "it" (prose style) exactly if not text structure, sentiment, vocabulary, etc?
What's the quality you're looking for that's not described in this review?
You claimed:
The paper does not demonstrate prompting a model, showing that with that prompt the writing is decent, and does not share such a prompt.
Fair enough, you want specifically prompts, here you are: https://github.com/blader/humanizer
In my experience fine tuning or specifically trained rewriting models work a lot better and fine tuning especially if you want to style copy a specific author. Mere prompting is not as good as that. But I still rate it as decent.
You made claims about prompts not me. Now I'm only asking you to back them up.
But you even look at the stuff you send me? This isn't a prompt, it's an agentic workflow. And this doesn't make the ai write differently it instructs the ai to modify already existing text.
But nitpicks aside, the results from something like this aren't even good, they're just plain bad. From your posting I assume you never tried it so I suggest you do that and experience the most soulless slop writing ever.
People keep saying this but never share the loras
More options
Context Copy link
More options
Context Copy link
I think the problem with AI regarding style is that it's incapable of making the various micro design choices a piece of writing involves. It's able to nail certain things that can be applied blanket-wise, like making the syntactic structure flow ultra smoothly or what have you, but when a decision requires a greater degree of discretion, you find that style of any variety simply isn't there. The things that humans would do to polish a piece are simply absent when the AI does it.
I think this gets to the root of why they randomly insert lists and stuff as well. There might be some kind of rote decision making tree where they go, 'Is this asking me a question about an array of topics? --> yes --> then split into a numbered list', which possibly works on average, but sticks out when it doesn't.
Finer styles like those affected by serious, accomplished writers quite possibly require the utmost of control over these micro decisions. If you attempt Hemingway's style and mostly get it, say to a degree of 80%, then the result might still fall flat. It might still collapse under the weight of its aspirations. So even a decent writer who makes a strong effort at recreating Hemingway might still show their limitations. An AI which doesn't come close is nothing more than a joke.
More options
Context Copy link
More options
Context Copy link
The other commenter said:
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link