Engagement poisoning of ChatGPT

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.

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.

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.

It's not diluting its answers, it's making them softer to accommodate the interests of many customers and to the detriment of others.

This is more analogous to Firefox semi-deprecating compact mode and marking it as unsupported. It hurts some users. It helps those with poor vision and motor skills by making everything 10 sizes too large. I will never forgive them, but Firefox is in the mode where it's actively hurting it's own product in an attempt to mimic it's competitor.

In neither case is this objectively hurting customers to benefit investors. In fact they've already stated that making the AI softer is more expensive. The reddit change was making it's product worse for customers in a pre-IPO cash grab. The shift from treating customers first to treating investors first to treating founders/ceos first is enshittification. A change to a product you don't like isn't enshittification.

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.

These are amazing.

Making users feel better is one of the usefulnesses of this technology. Factuality and scientific rigor are not something text generators are capable of due to the nature of the technology itself.

I would instead argue that being overly agreeable and not challenging the user may conflict with making the user feel better long-term.

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.