Show HN: Qwen3-4B with the AI writing tics trained out

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".

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.

What's with the very distracting cursors of others?

    and needs no system prompt

for https://slopwash.com I’ve started approaching this more as an eval problem than something to go post-training for. I’m excited to be trying these new Jev-type models in more of a harnessed approach. maybe some heavy LLM to measure preservation of intent

Why kill the em dashes? They are a legitimate mark — one that I have been using for years. On a Mac, you quickly get used to pressing shift-option-hyphen. Em dashes are typographically correct and should be used.

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 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...

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.

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?

Have you released the detector?

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.

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.

This still scores as 100% AI generated on tools like pangram.com.

It stil contains a triple construction, but ranks much cleaner on slop-cop.

[dead]