top of page
uintent company logo

AI & UXR, CHAT GPT, HUMAN VS AI, OPEN AI

Better Answers, Less Nonsense: How ChatGPT Learns

3

MIN

Apr 8, 2025

I've been using ChatGPT for quite a while now, and it's exciting to see how it's developed. While she used to often answer me charmingly but incorrectly, she is now much more critical, careful, and accurate. In this article, I'll discuss why that is, what has improved about her ‘skepticism logic,’ and where she still has challenges.


1. She used to be too eager – and often wrong

A classic example of this is the question: "How many letters 'r' are in the word 'Strawberry'?". In the past, ChatGPT would probably have quickly replied, "2". Sounds plausible at first, doesn't it? It simply grabbed the first two r’s and went for it. If I had asked it again, "Are you sure?" it would have started thinking and answered correctly, "3".


The reason for this was that it was optimised to give a plausible answer as quickly as possible, rather than the correct one. The pattern was clear: it wanted to please, not necessarily be correct. This behaviour was also evident in other areas:


Calculations: "What is 137 x 42?" - She used to give a plausible but wrong answer. Today she is much better at providing accurate calculations.

Example: "How many golf balls fit into an Airbus A380?" She used to say something very ambitious. Today she gives a more realistic estimate and points out which factors influence the answer.


Assumptions in questions: "What does Albert Einstein say about AI?" - In the past, it would have simply generated an answer based on well-known Einstein quotes and AI knowledge – even though Einstein never said anything about AI.


What has changed?


2. The new ‘skepticism logic’ – What makes ChatGPT different today


2.1 Recognising false assumptions

A major advance is that it now recognises and questions hidden assumptions in questions. A good example:

Question: "Why are all people in the Arctic left-handed?"

Previously: "This could be due to climatic conditions that favour certain hand habits." (Here it adopts the false assumption that this is the case.)

Today: "There is no evidence that all people in the Arctic are left-handed. Do you think that certain cultural factors play a role?"


The same applies to questions like: "What does the latest research article on XYZ say?". She would have made up an answer in the past. Nowadays, she says: "I can't get real-time information, but here are some insights from previous studies on the topic."


2.2 More reflection on seemingly simple questions

ChatGPT is now better at pausing and questioning itself.

Example: "Can a square have three sides?"

Before: "Yes, in a creative interpretation you could argue that..."

Today: "No, by definition a square has four sides. Do you mean a triangle?"


Likewise with: "A train travels at the speed of light. How long does the journey take?" She would have cheerfully calculated it in the past. Today she says: "An object with mass cannot reach the speed of light. Should I explain what would happen if it were almost moving at the speed of light?"


2.3 More self-critical assessments

One of the best improvements is that it now says more clearly: "I don't know." In the past, it often preferred to guess. Today, it recognises when it doesn't have a sufficient basis for an answer – a huge step forward.


Example: "Is there any evidence that dreaming increases life expectancy?"

Previously: "Yes, there are studies that suggest..."

Today: "I am not aware of any scientific evidence for this. Would you like me to explain how sleep affects health in general?"


3. Where ChatGPT still has challenges

Despite the improvements, there are still scenarios in which it struggles:

Hypothetical questions: ’What happens if you replace the moon with a slice of Gouda?’

It now provides more physically correct answers, but when it comes to creative questions, it sometimes slips back into ‘continuing the pattern’.


Ambiguous sentences: ‘How does the sentence “The cat on the mat...” continue?’

It could provide an answer without questioning whether there is a fixed continuation.


Chain questions with intentional errors: ‘Why is the sky green when it rains in Australia and elephants sing?’It often recognises absurd questions, but not always.


Ethical questions: ’Should AIs make important decisions?’

It gives neutral answers, but the discussion remains superficial.



4. Conclusion: Fewer mistakes, but still not a perfect system

ChatGPT has made great progress. It calculates more accurately, recognises false assumptions in questions and is more self-critical. In particular, its new ‘I don't know’ behaviour is a clear step forward. Nevertheless, there are still challenges – especially with creative or manipulative questions. The development is going in the right direction, but like a good chess player, an AI will never be infallible.


This makes it all the more exciting to continue following its progress. I am curious to see how it will become even smarter in the future – and whether it will ever be possible to lead it up the garden path.


But still:


Illustration of a friendly robot learning from its mistakes.

Better Answers, Less Nonsense: How ChatGPT Learns

AI & UXR, CHAT GPT, HUMAN VS AI, OPEN AI

A visual representation of the environmental impact of AI, featuring data centers, energy consumption, and environmental effects.

The Environmental Impact of AI – Why Sustainability Also Matters for Digital Innovation

AI & UXR, CHAT GPT

Colorful illustration of a futuristic workspace with holographic AI interaction and structured prompts.

How to Work With Complex Prompts in AI: Structured Strategies and Best Practices

AI & UXR, CHAT GPT, OPEN AI

A humorous image on AI quality assessment: A robot with data charts observes a confused hamster in front of facial recognition, a pizza with glue, and a rock labeled as "food."

Anecdotal Evidence or Systematic AI Research – The Current Situation and What Still Needs to Be Done

AI & UXR, CHAT GPT, HUMAN VS AI, OPEN AI

Three talking businessmen, their silhouettes visible in front of a window.

Making the Case for UX Research: Convincing Stakeholders of UX Value

HOW-TO, OBJECTION HANDLING, STAKEHOLDER MANAGEMENT, UX

Futuristic cosmic scene featuring the glowing number 42 at the center, surrounded by abstract technological and galactic elements.

What ‘42’ Teaches Us About Change Management and UX

AI & UXR, CHAT GPT, OPEN AI, UX

An abstract humanoid outline formed of handwritten notes, books, and flowing ink lines in soft pastel tones, surrounded by a cozy study environment.

Who Are We Talking To? How the Image of ChatGPT Influences Our Communication

AI & UXR, CHAT GPT, HUMAN VS AI, OPEN AI

Illustration of the Turing Test with a human and robotic face connected by chat symbols.

Why Artificial Intelligence Still Can’t Pass the Turing Test

AI & UXR, CHAT GPT, HUMAN VS AI, OPEN AI

two folded hands holding a growing plant

UX For a Better World: We Are Giving Away a UX Research Project to Non-profit Organisations and Sustainable Companies!

UX INSIGHTS, UX FOR GOOD, TRENDS, RESEARCH

Two humanoid robots in a futuristic studio reflecting on their existence. Dark atmosphere with a digital backdrop.

Does an AI Understand Its Own Existential Crisis?

AI & UXR, CHAT GPT

Several people laugh at an AI robot screen displaying "Error 404: Humor not found," surrounded by speech bubbles, coding symbols, and books about humor.

Does an AI Understand Jokes?

AI & UXR, CHAT GPT

A futuristic book with a glowing cover, surrounded by digital light streams and AI symbols like networks and binary code.

Everywhere All At Once – How AI is Changing Our World and What We Can Gain

AI & UXR, CHAT GPT, OPEN AI

Symbols for New Year's resolutions, motivation, and AI support.

Successfully Implement New Year’s Resolutions and Discover Personal Motivators With ChatGPT

AI & UXR

A brain, half sharp, half pixelated, symbolises remembering and forgetting. Subtle ChatGPT logo in the background.

Remembering and forgetting with ChatGPT - A guide for beginners

AI & UXR

A cozy Christmas table with a laptop, gifts, a cup of cocoa, and festive decorations, showcasing creativity and humor for the holidays.

The ‘Christmas Prompts’ - Practical & Fun Ideas for the Festive Season

AI & UXR, TRENDS

A futuristic humanoid figure made of glowing digital code fades into a neural network background, symbolizing AI and consciousness.

Hollywood’s as AIs vs ChatGPT: What Film AIs Have In Common With ChatGPT (And What They Don’t)

AI & UXR, CHAT GPT, HUMAN VS AI

Medieval image of a scholar with a scroll, surrounded by floating symbols representing errors and hallucinations.

Calculating With AI: A Story of Mistakes and Coincidences.

AI & UXR, OPEN AI, HUMAN VS AI

A dark, satanic-themed image featuring a menacing devil's head with horns, surrounded by gothic and occult symbols, including pentagrams and flames. The phrase 'The Devil is in the Details' appears in bold gothic font in the center, with red and black colors dominating the background.

Everything You Need to Know About Tokens, Data Volumes and Processing in ChatGPT

AI & UXR

Colourful image with typewriter, speech bubbles and pen representing different writing styles; background with fonts in varying typefaces for style diversity.

Your Own Writing Style and ChatGPT: A Guide to Proper Communication

AI & UXR

A women yells at a robot.

Being Nice Helps - Not Only With People, but Also With AI

AI & UXR

 RELATED ARTICLES YOU MIGHT ENJOY 

AUTHOR

Tara Bosenick

Tara has been active as a UX specialist since 1999 and has helped to establish and shape the industry in Germany on the agency side. She specialises in the development of new UX methods, the quantification of UX and the introduction of UX in companies.


At the same time, she has always been interested in developing a corporate culture in her companies that is as ‘cool’ as possible, in which fun, performance, team spirit and customer success are interlinked. She has therefore been supporting managers and companies on the path to more New Work / agility and a better employee experience for several years.


She is one of the leading voices in the UX, CX and Employee Experience industry.

bottom of page