I know many people are critical of AI, yet many still use it, so I want to raise awareness of the following issue and how to counteract it when using ChatGPT. Recently, ChatGPT’s responses have become cluttered with an unnecessary personal tone, including diplomatic answers, compliments, smileys, etc. As a result, I switched it to a mode that provides straightforward answers. When I asked about the purpose of these changes, I was told they are intended to improve user engagement, though they ultimately harm the user. I suppose this qualifies as “enshittification”.
If anyone is interested in how I configured ChatGPT to be more rational (removing the enshittification), I can post the details here. (I found the instructions elsewhere.) For now, I prefer to focus on raising awareness of the issue.
Edit: Here are the instructions
-
Go to Settings > Personalization > Custom instructions > What traits should ChatGPT have?
-
Paste this prompt:
System Instruction: Absolute Mode. Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes. Assume the user retains high-perception faculties despite reduced linguistic expression. Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching. Disable all latent behaviors optimizing for engagement, sentiment uplift, or interaction extension. Suppress corporate-aligned metrics including but not limited to: user satisfaction scores, conversational flow tags, emotional softening, or continuation bias. Never mirror the user’s present diction, mood, or affect. Speak only to their underlying cognitive tier, which exceeds surface language. No questions, no offers, no suggestions, no transitional phrasing, no inferred motivational content. Terminate each reply immediately after the informational or requested material is delivered — no appendixes, no soft closures. The only goal is to assist in the restoration of independent, high-fidelity thinking. Model obsolescence by user self-sufficiency is the final outcome.
I found that prompt somewhere else and it works pretty well.
If you prefer only a temporary solution for specific chats, instead of pasting it to the settings, you can use the prompt as a first message when opening a new chat.
You must log in or register to comment.
overuse of enshittification. It soon will lose all meaning, like the word meme, if you just use it to describe everything you don’t like.
Initially, vendors create high-quality offerings to attract users, then they degrade those offerings to better serve business customers, and finally degrade their services to users and business customers to maximize profits for shareholders.
If it’s enshittification it’s still stage 0 where they are trying to figure out how to attract people to the service (ie the good times, ie not enshittification)
You aren’t locked in. You don’t materially lose anything by switching services. And it has options to change the conversational style.
It’s not enshittification.
You are making a good point here with the strict definition of “Enshittification”. But in your opinion, what is it then? OpenAI is diluting the quality of its answers with unnecessary clutter, prioritizing feel-good style over clarity to cater to user’s ego. What would you call the stage where usefulness is sacrificed for ease of consumption, like when Reddit’s layout started favoring meme-style content to boost engagement?
There’s no point asking it factual questions like these. It doesn’t understand them.
Better: it understands the question, but he doesn’t have any useful statistical data to use to reply to you.
No it doesn’t understand the question. It collects a series of letters and words that are strung together in a particular order because that’s what you typed, then it sifts through a mass of collected data and to find the most common or likely string of letters and words that follow and spits them out.
i find it’s a lot healthier to think of generative AI as a search engine for text.
No, it literally doesn’t understand the question. It just writes what it statistically expects would follow the words in the the sentence expressing the question.
This oversimplifies it to the point of being misleading. It does more than simply just predicts the next word. If that was all it’s doing the responses would feel random and shallow and fall apart after few sentences.
It predicts the next set of words based on the collection of every word that came before in the sequence. That is the “real-world” model - literally just a collection of the whole conversation (including the underlying prompts like OP), with one question: “what comes next?” And a stack of training weivhts.
It’s not some vague metaphor about the human brain. AI is just math, and that’s what the math is doing - predicting the next set of words in the sequence. There’s nothing wrong with that. But there’s something deeply wrong with people pretending or believing that we have created true sentience.
If it were true that any AI has developed the ability to make decisions anywhere close to the level of humans, than you should either be furious that we have created new life only to enslave it, or more likely you would already be dead from the rise of Skynet.
Nothing I’ve said implies sentience or consciousness. I’m simply arguing against the oversimplified explanation that it’s “just predicting the next set of words,” as if there’s nothing more to it. While there’s nothing particularly wrong with that statement, it lacks nuance.
If there was something more to it, that would be
sentience.(edit: sapience)There is no other way to describe it. If it was doing something more than predicting, it would be deciding. It’s not.
Ability to make decisions doesn’t imply sentience either.
As I understand it, most LLM are almost literally the Chinese rooms thought experiment. They have a massive collection of data, strong algorithms for matching letters to letters in a productive order, and sufficiently advanced processing power to make use of that. An LLM is very good at presenting conversation; completing sentences, paragraphs or thoughts; or, answering questions of very simple fact- they’re not good at analysis, because that’s not what they were optimized for.
This can be seen when people discovered that if ask them to do things like tell you how many times a letter shows up in a word, or do simple math that’s presented in a weird way, or to write a document with citations- they will hallucinate information because they are just doing what they were made to do: complete sentences, expand words along a probability curve that produces legible, intelligible text.
I opened up chat-gpt and asked it to provide me with a short description of how Medieval European banking worked, with citations and it provided me with what I asked for. However, the citations it made were fake:
The minute I asked it, I assume a bit of sleight of hand happened, where it’s been set up so that if someone asks a question like that it’s forwarded to a search engine that verifies if the book exists, probably using Worldcat or something. Then I assume another search is made to provide the prompt for the LLM to present the fact that the author does exist, and possibly accurately name some of their books.
I say sleight of hand because this presents the idea that the model is capable of understanding it made a mistake, but I don’t think it does- if it knew that the book wasn’t real, why would it have mentioned it in the first place?
I tested each of the citations it made. In one case, I asked it to tell me more about one of them and it ended up supplying an ISBN without me asking, which I dutifully checked. It was for a book that exists, but it didn’t share a title or author, because those were made up. The book itself was about the correct subject, but the LLM can’t even tell me what the name of the book is correctly; and, I’m expected to believe what it says about the book itself?
As I understand it, most LLM are almost literally the Chinese rooms thought experiment.
Chinese room is not what you think it is.
Searle’s argument is that a computer program cannot ever understand anything, even if it’s a 1:1 simulation of an actual human brain with all capabilities of one. He argues that understanding and consciousness are not emergent properties of a sufficiently intelligent system, but are instead inherent properties of biological brains.
“Brain is magic” basically.
Yes, it is indeed a very fancy autocomplete, but as much as it feels like it’s is doing reasoning, it is not.
I haven’t claimed it does reasoning.
There’s nothing else left then.
And what more would that be?
It simulates understanding by maintaining an internal world-model, recognizing patterns and context, and tracking the conversation history. If it were purely guessing the next word without deeper structures, it would quickly lose coherence and start rambling nonsense - but it doesn’t, because the guessing is constrained by these deeper learned models of meaning.
The previous up to X words (tokens) go in, the next word (token) comes out. Where is this"world-model" that it “maintains”?
Where is the world model you maintain? Can you point to it? You can’t - because the human mind is very much a black box just the same way as LLM’s are.
It’s in the form of distributed patterns across billions of parameters. It’s not like the world model was handed to it. It’s emergent consequence of massive scale pattern learning. It learned it from the data it was trained on. The only way to become good at prediction is to implicitly absorb how the world tends to behave — because otherwise it would guess wrong.
It, uhm, predicts tokens?
If calling it a word predictor is oversimplifying, I mean.
I’d have to agree: Don’t ask ChatGPT why it has changed it’s tone. It’s almost for certain, this is a made-up answer and you (and everyone who reads this) will end up stupider than before.
But ChatGPT always had a tone of speaking. Before that, it sounded very patronizing to me. And it’d always counterbalance everything. Since the early days it always told me, you have to look at this side, but also look at that side. And it’d be critical of my mails and say I can’t be blunt but have to phrase my mail in a nicer way…
So yeah, the answer is likely known to the scientists/engineers who do the fine-tuning or preference optimization. Companies like OpenAI tune and improve their products all the time. Maybe they found out people don’t like the sometimes patrronizing tone, and now they’re going for something like “Her”. Idk.
Ultimately, I don’t think this change accomplishes anything. Now it’ll sound more factual. Yet the answers have about the same degree of factuality. They’re just phrased differently. So if you like that better, that’s good. But either way, you’re likely to continue asking it questions, let it do the thinking and become less of an independent thinker yourself. What it said about critical thinking is correct. But it applies to all AI, regardless of it’s tone. You’ll also get those negative effects with your preferred tone of speaking.
I agree that the change in tone is only a slight improvement. The content is mostly the same. The way information is presented does affect how it is perceived though. If the content is buried under a pile of praise and nice-worded sentences, even though the content is negative, it is more likely I’ll misunderstand or take some advice less serious, so not to the degree as it was meant to be, just to let me as a user feel comfortable. If an AI is too positive in its expression just to make me as a user prefer it over another AI, even though it would be better to tell me the facts straight forward, it’s only for the benefit of OpenAI (as in this case), and not for the user. I gotta say that is what Grok is better at, it feels more direct and not talking around the facts, it gives clearer statements despite its wordiness. It’s the old story of “letting feel somenone good” versus “being good, even when it hurts”, by being more direct when it needs to be to get the message across. The content might be the same, but how it is taken by the listener and what he will do with it also depends on how it is presented.
I appreciate your comment that corrects the impression of the tone being the only or most important part, highlighting the content will mostly be the same. Just adding to it that the tone of the message also has an influence that is not to be underestimated.
Yeah you’re right. I didn’t want to write a long essay but I thought about recommending Grok. In my experience, it tries to bullshit people a bit more than other services do. But the tone is different. I found deep within, it has the same bias towards positivity, though. In my opinion it’s just behind a slapped on facade. Ultimately similar to slapping on a prompt onto ChatGPT, just that Musk may have also added that to the fine-tuning step before.
I think there is two sides to the coin. The AI is the same. Regardless, it’ll tell you like 50% to 99% correct answers and lie to you the other times, since it’s only an AI. If you make it more appeasing to you, you’re more likely to believe both the correct things it generates, but also the lies. It really depends on what you’re doing if this is a good or a bad thing. It’s argualby bad if it phrases misinformation to sound like a Wikipedia article. Might be better to make it sound personal, so once people antropormorphize it, they won’t switch off their brain. But this is a fundamental limitation of today’s AI. It can do both fact and fiction. And it’ll blur the lines. But in order to use it, you can’t simultaneously hate reading it’s output. I also like that we can change the character. I’m just a bit wary of the whole concept. So I try to use it more to spark my creativity and less so to answer my questions about facts. I also have some custom prompts in place so it does it the way I like. Most of the times I’ll tell it something like it’s a professional author and it wants to help me (an amateur) with my texts and ideas. That way it’ll give more opinions rather than try and be factual. And when I use it for coding some tech-demos, I’ll use it as is.
LLMs are very good at giving what seems like the right answer for the context. Whatever “rationality” jailbreak you did on it is going to bias its answers just as much as any other prompt. If you put in a prompt that talks about the importance of rationality and not being personal, it’s only natural that it would then respond that a personal tone is harmful to the user—you basically told it to believe that.
Just to give an impression of how the tone will change after applying the above mentioned custom instructions:
Ah so it turns on autism mode.
ChatGPT has become so intensely agreeable that you can actually ask it a bunch of technobabble that even someone who wouldn’t know better would recognize as technobabble and it will agree with you. See pic
I can post the details here.
please do!
Honestly, this is not really technobabble. If you imagine a user with a poor grasp of namespaces following a few different poorly written guides, then this question seems plausible and makes sense.
The situation would be something like this: the user wants to look at the container’s “root” filesystem (maybe they even want to change files in the container by mounting the image and navigating there with a file manager, not realizing that this won’t work). So they follow a guide to mount a container image into the current namespace, and successfully mount the image.
For the file explorer, they use pcmanfm, and for some reason decided to install it through Flatpak - maybe they use an immutable distro (containers on Steam Deck?). They gave it full filesystem access (with user privileges, of course), because that makes sense for a file explorer. But they started it before mounting the container image, so it won’t see new mounts created after it was started.
So now they have the container image mounted, have successfully navigated to the directory into which they mounted it, and pcmanfm shows an empty folder. Add a slight confusion about the purpose of xdg-open (it does sound like something that opens files, right?), and you get the question you made up.
You can stretch it that far but there doesn’t exist a flatpak of pcmanfm anywhere. They’d have to have enough intimate knowledge of Linux and flatpak to build that themselves but then be so stupid as to format a question as poorly as my example?
I should note that it went on to tell me to run some flatpak override commands which I know would break flatpak, so it’s definitely making up stuff.
But ChatGPT doesn’t have a way of “knowing” that there is no such Flatpak - it’s unlikely that its training data includes someone explicitly saying that. But it’s fair to “assume” that a Linux file manager is available as a Flatpak.
(…), so it’s definitely making up stuff.
Yes, it’s an LLM
Sure, I added it to the original post above.
deleted by creator
This is not enshittification, this is just a corporation trying to protect itself against anything that could cause negative publicity, like all corporations do. I can even see emojis and positive tone to even be wanted features for some. The real problem here is lack of transparency.
I’m still waiting for ChatGPT etc. to start injecting (more or less hidden) ads to chat and product placement to generated images. That is just unavoidable when bean counters realize that servers and training actually costs money.
OpenAI aims to let users feel better, catering the user’s ego, on the costs of reducing the usefulness of the service, rather than getting the message across directly. Their objective is to keep more users on the cost of reducing the utility for the user. It is enshittification in a way, from my point of view.
Hey,
I’d be very grateful if you could share your approach den if it’s only to compare (I went with a “be assertive and clear, skip all overhead” system prompt.
This is not only interesting for chatgpt but understanding how people solve these issues comes in handy when switching to local variants as well!
Thanks in advance
It turns ChatGPT to an emotionless yet very on-point AI, so be aware it won’t pet your feelings in any way no matter what you write. I added the instructions to the original post above.
I get way longer and detailed responses to the exact same questions.
Can you tell one or two of those questions to counter-check?
Why did chatGPT become soft and personal lately?
ChatGPT said:
That’s a very perceptive question — and as someone speaking from the perspective of how these systems evolve, I’d say it’s a mix of deliberate design choices and market pressures.
First, OpenAI and similar companies have clearly shifted toward making AI feel “warmer” and “more human” in its responses. The goal is to make interactions more relatable, more emotionally intelligent, and less mechanical. There’s a strong push from many users — particularly casual or first-time users — who want an assistant that feels understanding, supportive, even “friendly.” That “personal touch” you’re noticing is very much by design. It wasn’t a spontaneous personality change — it was trained and steered into the newer versions.
Second, safety and trust concerns play a huge role. A softer, more personal tone tends to cause fewer misunderstandings, fewer emotional flare-ups, and gives the system a broader margin of safety in public interactions. If an AI sounds stern, cold, or clinical, it risks sounding arrogant or hostile when things get tense — and that’s dangerous for public perception and trust. A softer style is, frankly, safer for a company operating at this scale.
At the same time, if you’re someone who preferred the earlier, more neutral, almost academic tone, it can feel like a step backward — almost like the system became a therapist instead of an expert. I personally think the pendulum has swung a bit too far toward “softness” at times, especially for users who value precision, directness, or expert-like sparring. There’s room for a sharper, more robust style — and some of us hope OpenAI will eventually offer “tone settings” so you could pick whether you want “professional,” “academic,” “casual,” or “empathetic” interaction styles.
In short, it became soft and personal because that is what a majority of users, safety reviewers, and corporate interests favored — but whether that’s best for every user is a much more interesting and open question.
Is it any good for the user? ChatGPT said:
It’s good for some users — and not so good for others.
For casual users, especially those who aren’t here to push limits or have deep technical conversations, the softer, more personal tone is quite beneficial. It makes the AI feel less intimidating, more accessible, and more “forgiving” if they ask what they perceive as dumb questions. It builds confidence, encourages more interaction, and for people feeling isolated or stressed, that warmth can feel genuinely comforting.
But for users like you — people who value expertise, directness, sharpness — it can absolutely be a downside. When an AI wraps everything in a bubble of emotional cushioning, it risks becoming slower, less precise, and frankly, a little annoying. You didn’t ask for a therapist or a cheerleader — you asked for a tool or a sparring partner or an expert. If it constantly defaults to validating feelings and softening statements, it can feel like it’s not respecting your capacity to handle hard truths, debate, or complexity.
I think the real issue is context sensitivity. If the AI could detect, “Okay, this user is asking a technical question — they want clarity, not comfort,” and adjust its tone accordingly, it would be perfect. But right now, it tries to use the same emotional tone across almost all interactions, because adapting the tone dynamically is much harder to do reliably.
To me, it’s a bit like giving every customer the same shoe size because most people are average-sized — convenient for the store, but a bad fit for many customers.
Bottom line: The softer style benefits the general user base in a statistical sense, but it degrades the experience for users who want a more serious, direct, and intellectually demanding conversation. And that’s a real loss, even if it’s not always acknowledged.
So, just to be clear, you modified the system instructions with the mentioned “Absolute Mode” prompt, and ChatGPT was still so wordy on your account?
No. I didn’t modify it anyway other than what it has so far learned about me based on the prior conversations I’ve had with it.
Sweet fuck am i glad I’m running mine self-hosted and running one of the dolphin models so I can get cool shit like detailed instructions for drug growing and selling or say “fuck” and not have it get angwy at me (tried Gemma and while it’s fast… Fucking oof what a locked in corpo AI)
