This seems to be fundamentally based on n-grams and manually built regexes. "Slop", or more narrowly annoying -isms and model stereotypes, is not just repetitive n-gram sequences, mode collapse manifests itself semantically. Sometimes repetition/stereotyping is desirable (you need semantics to understand if it's the case), and sometimes undesirable repetition is undetectable by n-grams and regexes, especially in languages that rely on word formation. Fixing the mode collapse probably needs a sufficiently powerful reference model of semantic diversity, which doesn't currently exist.
Antislop: A framework for eliminating repetitive patterns in language models
71–80 of 119 posts
Re: Antislop: A framework for eliminating repetitive patterns in language models
#72Re: Antislop: A framework for eliminating repetitive patterns in language models
#73[dead]
Re: Antislop: A framework for eliminating repetitive patterns in language models
#74Earlier quoted context omitted.
Obviously nothing solid to back this up, but I kind of feel like I was seeing emojis all over github READMEs on JS projects for quite a while before AI picked it up. I feel like it may have been something that bled over from Twitch streaming communities.
Agree, this stuff was trending up very fast before AI. Could be my own changing perspective, but what I think is interesting is how the signal it sends keeps changing. At first, emoji-heavy was actually kind of positive: maybe the project doesn't need a webpage, but you took some time and interest in your README.md. Then it was negative: having emoji's became a strong indicator that the whole README was going to be v…
There’s a pattern to emoji use in docs, especially when combined with one or more other common LLM-generated documentation patterns, that makes it plainly obvious that you’re about to read slop.
Even when I create the first draft of a project’s README with an LLM, part of the final pass is removing those slop-associated patterns to clarify to the reader that they’re not reading unfiltered LLM output.
Re: Antislop: A framework for eliminating repetitive patterns in language models
#75Earlier quoted context omitted.
Man it is truly difficult to overstate all the behavioral health issues that have been emerging.
These are just symptoms and not the cause.
This comes across as an unnecessary oversimplification in service of handwaving away a valid concern about AI and its already-observed, expanding impact on our society. At the very least you should explain what you mean exactly.
Alcoholism can also be a symptom of a larger issue. Should we not at least discuss alcohol’s effects and what access looks like when deciding the solution?
Re: Antislop: A framework for eliminating repetitive patterns in language models
#76Chatgpt-5:
Oof—-gotcha here’s how I’d handle that
Clutch choice—-here’s a few refinements
Sweet—-let me just…
Ok, here’s the receipts
I love your passion! Let’s try to keep it civil ok?
(Thinking) the user still appears annoyed
—————————————-
I think this annoys them also and yet they can’t change it? Or are they not dogfooding?
Re: Antislop: A framework for eliminating repetitive patterns in language models
#77That’s not what “slop” means. Slop is output produced by generative AI without regards to its quality, not the telltale tics that current models tend to exhibit.
>That’s not what “slop” means It's a new term so the meaning hasn't had a chance to settle. It's generally considered to be a negative term, so there's motivation for people to expand the definition to include things that they don't like. It is much easier to subvert a category than it is to make an argument for an individual item. Imagine if people accept that falling rocks kill hundreds of people every year, and yo…
I've seen it used enough that it's clear to me that the implied definition is "low-quality and/or low effort AI-generated content", and the actual usage is "AI generated content that I don't like". But both of those definitions very clearly refer to the piece of content as a whole, rather than specific parts of the content.
Re: Antislop: A framework for eliminating repetitive patterns in language models
#78I've been using ChatGPT fairly regularly for about a year. Mostly as an editor/brainstorming-partner/copy-reviewer. Lots of things have changed in that year, but the things that haven't are: * So, so many em-dashes. All over the place. (I've tried various ways to get it to stop. None of them have worked long term). * Random emojis. * Affirmations at the start of messages. ("That's a great idea!") With a brief pause w…
You can take my em-dashes from my cold, dead hands—I use them all the time.
On iOS in particular the longer dash variants are easy to access — via long pressing dash.
Anecdotally, I use them less often these days, because of the association with AI.
Re: Antislop: A framework for eliminating repetitive patterns in language models
#79Earlier quoted context omitted.
Don't forget the classic: "It's not just X—it's Y."
This is the main thing that immediately tells me something is AI. This form of reasoning was much less common before ChatGPT.
I don't think this is true. The LLMs use this construction noticeably more frequently than normal people, and I too feel the annoyance when they do, but if you look around I think you'll find it's pretty common in many registers of human natural english.
Re: Antislop: A framework for eliminating repetitive patterns in language models
#80This is the epitome of patching symptoms rather than treating the disease. Even if you suppress the obvious syntactic slop like 'it's not X but Y', you have no reason to believe you've fixed mode-collapse on higher more important levels like semantics and creativity. (For example, Claude LLMs have always struck me as mode-collapsed on a semantic level: they don't have the blatant verbal tics of 4o but somehow they still 'go in circles'.) Which will potentially severely hinder the truly high-value applications of LLMs to creative applications like frontier research. To the extent that this succeeds in hiding the brain damage in contemporary LLMs, it arguably is a cure worse than the disease.