Models have proclivities, and many people use the same model.
Imagine all books on earth were written by just 5 people - and worse, they could not remember what they had written yesterday. You would quickly get tired of reading the same flourishes and patterns over and over.
Whatever style models currently in use have, that's what people are going to be tired of, and it's what they're going to recognize as "AI".
The most difficult thing in doing it yourself is knowing what to ask for. I can ask my model to talk like a caveman or like a Baltic pirate. But asking for something more nuanced, in the range of regular speech, requires the correct lingo
I'm sure it's trivial for somebody who has studied communication or contemporary linguistics, just as it's trivial for me to ask an LLM for tenant-isolation using row-level security in an app
Why would you support this sort of projects?
LLM text should be spottable for as long as possible, otherwise human communication and expression on the internet will be killed.
I don't understand why this is a feature and what it brings other than shout "you are being watched by random others".
Exited the site before ending the first block.
Side note but the multi-user cursors was a super cool feature, not sure it was relevant to this article but would love to see it on more interactive pieces (a la The Pudding, etc.)
The tell tell sign for me is that it's still incredibly hard to read. AI tend to write in a style that I'm unable to easily read (humans does that as well sometimes). I constantly have to go back and re-read the previous sentence, because the text simply doesn't register.
A next step I'd suggest is asking the LLM to use shorter words when available.
Is it still capable of writing an essay about AI writing tics or has the very means of producing said tics, even when the model is asked to do so to demonstrate, now abitterated?
Applause earned. Neat results especially out of such a small model.
Separately we have overlap between AI slop styles and right for the situation writing styles which this highlights.
Using the new CRM example, the clean version looks like a millennial student who rambled on a page, and the AI slop version looks like a draft I could send for PR to corporate managers. I buy the former looks more real, but it also looks sloppy and doesn’t work for most of my use cases.
When I was in school, the structured essay style of the “slop” examples was encouraged and I see it continue to resonate in corporate. The cleaned up versions here def have use cases - reviews for example.
Main point - different styles for different situations and our AI slop versions vs humanized versions both overlap different areas of the “ideal” we continue to look for.
Models have proclivities, and many people use the same model.
Imagine all books on earth were written by just 5 people - and worse, they could not remember what they had written yesterday. You would quickly get tired of reading the same flourishes and patterns over and over.
Whatever style models currently in use have, that's what people are going to be tired of, and it's what they're going to recognize as "AI".
I predict by the end of the year they'll have a style/voice selector for responses.
You can already do that in your agents.md file, of course, or ask for a re-write and dodge the sameness.
The most difficult thing in doing it yourself is knowing what to ask for. I can ask my model to talk like a caveman or like a Baltic pirate. But asking for something more nuanced, in the range of regular speech, requires the correct lingo
I'm sure it's trivial for somebody who has studied communication or contemporary linguistics, just as it's trivial for me to ask an LLM for tenant-isolation using row-level security in an app
This is not the first deslop. The true pioneer is this dude: https://huggingface.co/sam-paech/gemma-3-27b-it-antislop. This model is a perfectly usable, full size not-toyish model.
Why would you support this sort of projects? LLM text should be spottable for as long as possible, otherwise human communication and expression on the internet will be killed.
What's with the very distracting cursors of others?
I don't understand why this is a feature and what it brings other than shout "you are being watched by random others". Exited the site before ending the first block.
The ancients brought us "reading mode" in browsers as an escape hatch for exactly this kind of cruelty
Exactly. I was interested in the article but I don't have time for that nonsense.
Agreed. In the upper right corner there's a "hide" button that I immediately clicked. Then read (ok, skim read) the article.
Agreed. Just because you _can_ do a thing, doesn't mean you should.
All it is missing now is a chat and a friend/follow feature.....
There's a "hide" button in the top right corner
Nobody knows what it means, but it's provocative. It gets the people going
going... away?
Side note but the multi-user cursors was a super cool feature, not sure it was relevant to this article but would love to see it on more interactive pieces (a la The Pudding, etc.)
It's definitely a slight improvement, but it is still rather obvious that the output is AI-written :(
The tell tell sign for me is that it's still incredibly hard to read. AI tend to write in a style that I'm unable to easily read (humans does that as well sometimes). I constantly have to go back and re-read the previous sentence, because the text simply doesn't register.
A next step I'd suggest is asking the LLM to use shorter words when available.
Did you check this? https://huggingface.co/sam-paech/gemma-3-27b-it-antislop
The q4 loops after 16k tokens generated. Great idea though, hope to see more models like it. Thanks. https://huggingface.co/erikkannike/qwen3-4b-deslop-v4/discus...
Now can I have a model with the AI writing tics trained to the max?
I want my boss to know I'm a Good Boy using AI.
Is it still capable of writing an essay about AI writing tics or has the very means of producing said tics, even when the model is asked to do so to demonstrate, now abitterated?
Applause earned. Neat results especially out of such a small model.
Separately we have overlap between AI slop styles and right for the situation writing styles which this highlights.
Using the new CRM example, the clean version looks like a millennial student who rambled on a page, and the AI slop version looks like a draft I could send for PR to corporate managers. I buy the former looks more real, but it also looks sloppy and doesn’t work for most of my use cases.
When I was in school, the structured essay style of the “slop” examples was encouraged and I see it continue to resonate in corporate. The cleaned up versions here def have use cases - reviews for example.
Main point - different styles for different situations and our AI slop versions vs humanized versions both overlap different areas of the “ideal” we continue to look for.
I saw those moving dots and snap-closed the page.
Impressed how little hardware is needed to train this.