Why all AI content sounds exactly the same (and how to fix it)

Drea Says Product Things

SubscribeSign in

Why all AI content sounds exactly the same (and how to fix it)<br>AI Slop has taken over. Learn why and how to make your prompts fight back.

andrea saez<br>Aug 16, 2026

Share

Ever notice that AI copy has a smell?<br>It’s the distinct smell of confident bullsh*t.<br>All AI copy contains the same rhythm, structure, landing, and shitty dismount no matter who prompted it (I was once a gymnast, stay with me here.) AI slop is everywhere, and the reason is more than just lack of copywriting skills.<br>TL;DR

As previously explained, LLMs don’t pick words freely. They sample from a probability distribution over what to say next, the first during pre-training, and the second during alignment training, which measurably narrows how many different ways the model is willing to answer the same question.<br>Nothing learns or explores at the moment you hit send, as every reply is one draw from an already fixed distribution. The one lever you actually hold is the prompt, because it reshapes which slice of that distribution gets sampled. If you provide enough specificity during prompt, the ‘sameness’ behind the AI sloppy output gets diluted.<br>How models sample words

At each step of generating a response, LLMs produce a probability score for every possible word that follows based on everything written so far. That scoring happens through layers of attention (the transformer architecture), which weigh which earlier words matter most for predicting the next one, against a huge table of learned word representations (embeddings) built during training. Generation then draws one word from that scored list, more likely to land on high-probability words, with a setting called temperature controlling how much randomness enters the draw.

Repeat that one word at a time until the response ends, and you've described the entire process. There’s no separate creativity step and no separate correctness step. There’s one distribution per word, and one sample from it.<br>Training narrows that distribution before you type anything

During pre-training, a model learns from a huge slice of existing text which continuations are most common, and “common” means average. It’s cross-pollinating patterns it has already seen, so the most probable next word is the most conventional one.<br>The second narrowing is sharper, and it happens in the stage that makes a model helpful and safe to ship, aka Reinforcement Learning from Human Feedback (RLHF).<br>A 2024 study from Kirk tested this, comparing supervised fine-tuning against full RLHF training across multiple models and tasks. RLHF generalized better to new situations, but it substantially reduced output diversity, a well-documented effect the field calls mode collapse.<br>In simple terms, the model converges toward a smaller set of safe, high-reward answers instead of exploring the many valid ones.<br>By the time produces a single word for you, the distribution behind your reply has already been compressed twice; once toward the statistically average continuation, and once toward whatever answer scores best with human raters.<br>Nothing is learning while you type

Understanding this informs what you should expect from a refined prompt. The model’s weights are frozen at inference. This means there’s no learning, no exploration, and no memory forming while it writes your response. Every reply is one sample from a distribution that was already fixed before your conversation started.<br>Scary, right?<br>That’s good news and bad news at once. (Sit tight!)<br>The bad news : you can’t train the sameness out of a single session.<br>The good news : the distribution is conditional on what you feed it, which means the input is the one part of this whole system still under your control.<br>What you control : which distribution it samples from.<br>The prompt doesn’t change the model. It changes which part of the model’s existing distribution gets sampled.<br>If you ask an obvious question the most probable answer is the obvious one, because that’s the region of the distribution your prompt pointed at. Ask a sharper question, and the most probable answer moves with it.<br>A few prompts that reliably move it:<br>What’s the contrarian take?

What would you say if the obvious angle were off the table?

Write this as if conventional wisdom is wrong.

What would make our audience stop and push back?

What would our competitor never say?

These will change which slice of a fixed distribution you’re asking it to draw from, and that’s the whole difference between generic and specific outputs.<br>How to fix the “sameness” problem

Prompting alone gets you partway there because it reshapes the distribution for a single message at a time. If you want the model consistently producing your voice instead of the training-data average, give it something narrower to condition on every time.<br>1. Build a small RAG system

Feed a model like Claude a folder of your own published work and set...