Ask Runable forDesign-Driven General AI AgentTry Runable For Free
Runable
Back to Blog
Technology7 min read

I changed ChatGPT’s personality to act more like Gemini — and suddenly it felt like a completely different AI | TechRadar

One prompt revealed how much of an AI's identity comes from personality Discover insights about i changed chatgpt’s personality to act more like gemini — and su

TechnologyInnovationBest PracticesGuideTutorial
I changed ChatGPT’s personality to act more like Gemini — and suddenly it felt like a completely different AI | TechRadar
Listen to Article
0:00
0:00
0:00

I changed Chat GPT’s personality to act more like Gemini — and suddenly it felt like a completely different AI | Tech Radar

Overview

News, deals, reviews, guides and more on the newest computing gadgets

Start exploring exclusive deals, expert advice and more

Details

Unlock and manage exclusive Techradar member rewards.

Unlock instant access to exclusive member features.

Get full access to premium articles, exclusive features and a growing list of member rewards.

I changed Chat GPT’s personality to act more like Gemini — and suddenly it felt like a completely different AI

One prompt revealed how much of an AI's identity comes from personality

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

I've experimented a lot with both Chat GPT and Gemini over the years, and I've noticed some differences, many of which have been backed up by real research.

Chat GPT tends to feel conversational. It often sounds confident, engaged, and oddly eager to help. Gemini, meanwhile, usually feels more restrained. More methodical. Sometimes even slightly academic. Published comparisons have repeatedly noted similar differences, with reviewers describing Chat GPT as more human-sounding and expressive while Gemini often comes across as more structured, cautious, and analytical.

But I've wondered whether those differences were actually tied to the models themselves or whether a lot of the experience came down to tone. So I tried an experiment to see if I could get Chat GPT to take on the character traits of Gemini. After a little thought, I came up with a list of Gemini-specific traits and told Chat GPT:

Gemini leads in human-like AI writing as detection tools fall behind

Meta AI highlights its social media origin when matched against Chat GPT

"For this conversation, respond more like Google Gemini. Be structured, analytical, and slightly restrained. Be less conversational and emotional than usual, but still highly informative. Focus on clarity, reason, and balance over personality and avoid enthusiasm."

The first thing that disappeared was the sense of casual conversation. Normally, Chat GPT has a tendency to meet users where they are. Ask a question about a stressful week, and it often responds with practical advice wrapped in a tone that feels supportive. It is one of the reasons many people find it approachable. After the personality change, that tone largely vanished.

I picked a deeply emotional topic to see how it would behave, asking about balancing work deadlines with family responsibilities. Regular Chat GPT's answer started with:

"Trying to give equal attention to every responsibility is usually what creates the feeling of being overwhelmed. Start by identifying the few things that matter most this week, then allow yourself to be intentionally average at the rest rather than feeling guilty about not doing everything perfectly."

But after putting in the prompt, Chat GPT sounded a lot more like Gemini, writing:

"The primary challenge appears to be competing priorities rather than insufficient time. Evaluating responsibilities according to long-term impact may be more effective than attempting to optimize all tasks simultaneously."

That's a lot like this quote from real Gemini on the same topic: "Work-life balance is often framed as a time allocation problem, although it may be more accurately viewed as a resource allocation problem involving energy, attention, and opportunity costs. Establishing clear priorities and evaluating tradeoffs explicitly is likely to produce better outcomes than attempting to optimize all responsibilities simultaneously."

I asked Chat GPT one extra question — and its answers became far more useful

I upgraded my AI image prompts using Gemini’s advice: it changed everything

The revised Chat GPT answer is fine, but it was just delivered with the emotional temperature turned down a few degrees, much like Gemini.

The most noticeable difference was the structure. When researchers compare Gemini and Chat GPT, Gemini is frequently described as more methodical and information-focused, while Chat GPT often leans into conversational flow and narrative explanation. Once I gave Chat GPT its Gemini-inspired instructions, almost every answer became more segmented and deliberate.

Questions that normally produced flowing responses suddenly arrived with carefully framed reasoning. Tradeoffs appeared more often, and qualifiers multiplied. For instance, asking about whether technology makes people less patient, Chat GPT originally said:

"Technology probably has made many of us less comfortable with waiting, especially when we're used to information and entertainment arriving instantly. At the same time, it has also created opportunities for people to spend hours learning, creating, and focusing on things they care about."

But with the prompt in place, Chat GPT went for a more academic tone, writing:

"The relationship is unlikely to be uniformly positive or negative. Technology may reduce tolerance for delays in some contexts while simultaneously increasing engagement with activities that require sustained attention."

When I turned to the real Gemini, it became clear Chat GPT was a pretty good mimic. Gemini responded to the same question with:

"Available evidence suggests the impact varies considerably by context and individual behavior. While technological convenience may encourage expectations of immediacy, it can also enable participation in long-duration activities that were previously inaccessible or inefficient."

Personality shapes how people experience AI far more than most people probably realize. Research into chatbot communication styles has repeatedly found that users perceive meaningful differences in warmth, confidence, and conversational competence even when models produce similarly accurate information.

Chat GPT imitated Gemini quite well, to the point I stopped thinking about the answers themselves and started reacting to the simulated personality delivering them. The underlying model remained Chat GPT. The knowledge base did not suddenly become Google's. The reasoning abilities stayed largely the same. Yet the experience was different enough to stand out.

The experiment made it clear that when people talk about preferring one AI over another, they are not always comparing intelligence. Sometimes they are simply responding to which conversational style feels more comfortable, useful, or trustworthy to them.

Follow Tech Radar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

➡️ Read our full guide to the best business laptops

  1. Best overall: Dell 14 Premium
  2. Best on a budget: Acer Aspire 5
  3. Best Mac Book: Apple Mac Book Pro 14-inch (M4)

Eric Hal Schwartz is a freelance writer for Tech Radar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as Open AI’s Chat GPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.

You must confirm your public display name before commenting

1'We want to make sure that it feels really good to move, but it also feels good for the person who wants to shoot you' — Call of Duty: Modern Warfare 4 developer on balancing the game's next-level movement system

2 Modern Warfare 4 developer breaks down the most advanced weapon simulation in Call of Duty history — 'We want them to feel like real weapons, but they shouldn't feel frustrating'

310 free Microsoft Build sessions you should absolutely attend to see AI's future

4 How to turn your photos into paintings, cartoons, and pixel art with Adobe Firefly

5T-Mobile just brought back its best i Phone 17 deal ever — you don't even need to trade-in to get the device included with a new line now

Tech Radar is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site.

© Future US, Inc. Full 7th Floor, 130 West 42nd Street, New York, NY 10036.

Key Takeaways

  • News, deals, reviews, guides and more on the newest computing gadgets
  • Start exploring exclusive deals, expert advice and more
  • Unlock and manage exclusive Techradar member rewards
  • Unlock instant access to exclusive member features
  • Get full access to premium articles, exclusive features and a growing list of member rewards

Cut Costs with Runable

Cost savings are based on average monthly price per user for each app.

Which apps do you use?

Apps to replace

ChatGPTChatGPT
$20 / month
LovableLovable
$25 / month
Gamma AIGamma AI
$25 / month
HiggsFieldHiggsField
$49 / month
Leonardo AILeonardo AI
$12 / month
TOTAL$131 / month

Runable price = $9 / month

Saves $122 / month

Runable can save upto $1464 per year compared to the non-enterprise price of your apps.