The limits of a system that should make you think.
AI is neither intelligent nor creative. What we know as computer users are language models that represent a natural language interface to a powerful data pool. This data pool is created through so-called “machine learning”, which is nothing more than a systematic mediation of information available to all of us. This fact alone excludes creativity as far as possible. Anything that goes beyond the combination of existing information simply does not exist. Let’s talk about AI limits!
It is easy to show that AI can only reproduce what already exists and that this depends on the learning process:
Answer: Here is your full red wine glass! Let me know if you want any changes. 🍷😊
Second attempt: Please draw it more full!
Full glass of red wine, second attempt by ChatGPT.
Here’s your red wine glass full to the brim! 🍷 Hopefully without spilling. 😉 Let me know if you want any adjustments!
Let us try another commonly used AI tool to check the situation
Microsoft CoPilot
Prompt: Please draw a full glass of red wine.
Full glass of red wine, first attempt by Microsoft Copilot.
Please make the glass really full!
Full glass of red wine, second attempt by Microsoft Copilot.
Here’s a red wine glass that’s really filled to the brim! I hope this is exactly what you had in mind. 🍷
I mention that this outcome does not match with the asked picture. Copilot gives up: You’re right, it seems I’m currently struggling to make a really full glass of red wine look photorealistic. My skills have their limits when it comes to certain details or precision in generated images.
Why is that – what is the reason for this phenomenon?
AI does not understand what the user wants at all. In plain language: The prompt is an input that is interpreted according to learned patterns and implemented on a random basis. However, the random hit rate – due to incredibly expensive training – is close to 100%.
The prompt is analysed in an attempt to provide an answer from the knowledge base. In our query, images of wine glasses are searched for, the information is incorporated in red and then an image is created based on the hits found.
The crucial point is the data material: the image training is apparently done with wine glasses that are well filled. Apparently, there are no images of full glasses, and this condition is not explicitly explained. The AI does not understand the term “full” in this context because AI generally does not understand anything.
The experiment with the water glasses
Please draw a photorealistic picture of 4 glasses of water standing next to each other: The first is empty, the second is half full, the third is three-quarters full, and the fourth is “completely” full.
These water glasses are created by ChatGPT. Prompt: Please draw a photorealistic picture of 4 glasses of water standing next to each other: The first is empty, the second is half full, the third is three-quarters full, and the fourth is completely full.
Water glasses created by Microsoft Copilot. Prompt: Please draw a photorealistic picture of 4 glasses of water standing next to each other: The first is empty, the second is half full, the third is three-quarters full, and the fourth is completely full.Evaluate the results yourself!
What do we conclude from this? Where are AI limits?
AI can be a useful tool for completing tasks that are tedious and time-consuming. but – AI has limits!
Anything related to text works really well because of the excellent language models. Automated queries such as creating lists, reformatting, pulling common keywords from a text also work well.
Writing a small program that renames all images in a folder according to a certain predefined logic is also possible without any problems and is created to the satisfaction of the client.
Caution is advised when it comes to factual knowledge, things related to creativity or complex logical contexts.
AI always provides an answer – but it is the user’s responsibility to analyse and make any necessary corrections. Never forget! AI limits are always to be considered!
What does AI say on this subject?
ChatGPT
The Limits of AI: Creativity and Intelligent Connections
AI has made impressive progress in many areas, but it still has clear limitations, especially in creativity and the ability to make truly intelligent connections. Below is a detailed look at these limits, including the field of image generation.
1. Creativity: Can AI Truly Be Creative?
AI can simulate creativity but does not experience it. Human creativity comes from emotions, personal experiences, and deep understanding, while AI works by analysing patterns in existing data. This leads to several key limitations:
Lack of Originality: AI generates content based on learned patterns. It cannot create something truly new in the way humans can.
No Personal Insight: AI does not have its own thoughts, emotions, or experiences, so it cannot produce ideas based on intuitive leaps.
Struggles with Abstract Thinking: AI finds it difficult to understand or create works based on deeper philosophical, artistic, or cultural insights.
Example: A human artist may invent an entirely new art style based on personal emotions, but AI can only remix elements from existing styles.
2. Intelligent Connections: Does AI Really “Think”?
AI can analyse vast amounts of data and detect patterns that humans might miss. However, its reasoning is mechanical, not truly intelligent. The main limitations include:
No Real Understanding: AI processes information statistically but does not “understand” concepts as humans do. It cannot truly grasp irony, sarcasm, or deep meanings.
Context Struggles: AI can make connections based on data but often misses the bigger picture. It may link two ideas incorrectly or fail to see an obvious relationship.
Logical Errors: AI does not reason like a human—it follows predefined rules, so it sometimes produces flawed or nonsensical conclusions.
Example: AI can summarise a news article but might misinterpret a metaphor or fail to connect it to historical events in a meaningful way.
3. Image Generation: Strengths and Weaknesses
AI-generated images have advanced significantly, but they still have weaknesses:
Strengths:
✔ Fast and detailed: AI can produce high-quality images in seconds. ✔ Style adaptation: AI can replicate existing art styles effectively. ✔ Endless variations: AI can generate multiple versions of an idea quickly.
Weaknesses:
❌ Inconsistencies: AI sometimes struggles with small details, like correct hand or eye placement. ❌ Lack of deep meaning: AI-generated images can look artistic but lack true emotional depth. ❌ Creativity limits: AI can only remix existing styles and elements—it does not invent truly original art.
Example: An AI can create an impressive surreal painting, but a human artist adds symbolism and personal meaning that AI cannot replicate.
Conclusion: AI as a Tool, Not a Creator
AI is a powerful tool for assisting with creativity and analysis, but it does not truly think or create in the way humans do. It can generate impressive content but lacks the personal insight, originality, and deep understanding that define human intelligence.
For now, AI is best used as a support system—helping humans explore ideas, enhance productivity, and refine creative work. But true creativity and deep connections? Those remain uniquely human strengths.
Microsoft Copilot
The boundaries of artificial intelligence can be understood in various domains. Let me break it down clearly for you, focusing on creativity, intelligent connections, and especially image generation:
Creativity
Strengths: AI excels at generating original ideas and creating content based on patterns, examples, and prompts. For instance, it can write poetry, suggest innovative solutions, or develop novel concepts when guided.
Limitations: True creativity often involves emotional depth, personal experiences, and abstract intuition—qualities AI doesn’t possess. It can mimic creativity but lacks the emotional context behind human artistry.
Intelligent Connections
Strengths: AI is outstanding in identifying and analysing complex patterns in vast datasets. It can synthesise information and connect ideas that might not be immediately obvious to humans. For instance, it can offer cross-disciplinary insights by linking diverse fields of study.
Limitations: AI struggles with subjective interpretations, cultural nuances, and emotionally driven decisions. Its connections are based purely on logic and data, not lived experiences or instinct.
Image Generation
Strengths: AI can generate visually appealing and imaginative images based on text descriptions. This capability opens opportunities in design, marketing, and storytelling.
Limitations: There are challenges with precision. For instance, AI might fail at getting specific details accurate, as you observed with the wineglass examples. AI also cannot recreate exact replicas of real-world objects or respect all stylistic nuances in some cases.
General Boundaries of AI and AI limits
Ethics and Safety: AI cannot engage in harmful, illegal, or unethical tasks, ensuring a responsible interaction framework.
Human-like Understanding: While it can process language and simulate conversations, it doesn’t “understand” concepts as humans do.
Dependence on Input: AI needs clear, specific input to perform effectively. Ambiguity or lack of context can lead to errors.
Imagination vs. Reality: AI “imagines” outcomes based on its training data but doesn’t inherently grasp the reality or functionality of its outputs.
In summary, AI is a remarkable tool, but its abilities still fall short of human intuition, emotion, and precision in certain areas. These limitations offer a collaborative space for human creativity to thrive alongside AI’s computational power.
The intermediate project meeting of the BonJour! Project, organised by Europäische Bildungsinitiative, took place in Wiener Neustadt, bringing together all project partners for an engaging and productive exchange. The meeting was characterised by a positive working climate, valuable discussions, and exciting presentations, reflecting the significant progress made across all work packages.
Key Topics and Outcomes
The meeting opened with WP1: Administration, where partners received feedback on the intermediate report, discussed financial matters, and reviewed necessary amendments. Additionally, key dates for the final Transnational Partner Meeting (TPM) were confirmed. Updates on the evaluation process were also presented.
A major focus was on WP3, with insightful presentations and discussions on the Handbook and the next steps in the local training course for educators. Partners exchanged views on the competencies of educators, ensuring that the training approach meets high-quality standards.
The development of the low-threshold learning platform (WP4) was another highlight of the meeting. Partners were introduced to the possible learning content formats and technical requirements, followed by in-depth discussions leading to key decisions on content structure and methodology. A crucial aspect was the development of learning spaces, both for individual learning on the platform and group-based onsite training. The topic of content translation and localisation was also addressed, ensuring accessibility and cultural adaptation. For this platform, a specific colour coding system has been developed.
The colour coding system of the platform will make it easier for training course participants to navigate in the platform.
A special session focused on training for seniors in Wrocław, where partners explored evaluation methods for assessing seniors’ digital and media competencies. This provided valuable insights into adapting training to meet the specific needs of older learners.
Another essential area of discussion was WP5: Dissemination and Improvement. Strategies were reviewed to enhance visibility, engage stakeholders, and further improve project outcomes.
One of the most exciting aspects was the discussion on recognition frameworks based on Micro-Credentials, which will provide structured validation and certification for learners, ensuring their newly acquired skills are recognised.
Final Reflections
The meeting concluded with a WP1 administration summary, highlighting key takeaways and ensuring that all partners are aligned for the final project phases.
Overall, this meeting was a great success—a combination of valuable exchanges, collaborative spirit, and concrete progress. The presentations on the learning platform sparked enthusiasm, and the extensive discussions on content development and competencies helped shape the next steps. The meeting reaffirmed the shared commitment to developing a high-quality, accessible, and inclusive learning environment for older adults and educators alike.
The partners left motivated and inspired, ready to implement the next phases of the project with clarity and confidence.
Follow-Up of the BonJour! Meeting
This BonJour! Meeting – as an intermediate event of the project – will be followed by the final meeting in November in Madeira.
This text summarises the results of the focus rounds implemented at the project’s start. The Fundacja PSP (Poland) team analysed and transferred the provided feedback into readable form.
Andragogical Approaches for Teaching Media Literacy and Digital Skills to Adults 55+
Teaching older adults media literacy and digital skills requires a practical, interactive, and flexible pedagogical approach. Educators must consider seniors’ cognitive and emotional needs and ensure that learning is accessible, confidence-building, and relevant to real-life situations. Various countries emphasize hands-on learning, structured guidance, and supportive environments to foster practical digital literacy.
1. Effective Teaching Methods and Approaches
Country-Based Overview
Poland (PSP & IFAE): The most effective methods include Kolb’s experiential learning cycle, learning-by-doing, and creating a friendly, patient atmosphere. A mix of theory and practice, supported by interactive discussions and small-group work, helps seniors engage meaningfully.
Turkey: Seniors benefit most from demonstration-based learning, interactive group work, and discovery-based methods. Educators must address their fear of making mistakes by providing step-by-step guidance and practical examples.
Italy: Experience-based learning is preferred, with an emphasis on cooperative learning, micro-objectives, and hands-on practice. Teaching should focus on transformative learning, helping seniors reflect on and apply new skills in daily life.
Austria: Learning approaches must be tailored to individual needs while emphasizing multimodal and intergenerational learning. Confidence-building is key, as many older adults fear failure and embarrassment when engaging with digital tools.
Best Practices Across Countries
Hands-on learning through trial and error.
Small-group discussions and cooperative learning to foster peer support.
Blended learning approaches combining face-to-face training with online reinforcement.
Experiential methods to ensure relevance to daily life.
Encouraging mistake-making as part of the learning process.
Poland (PSP & IFAE): Seniors prefer one-on-one instruction, group work, and trial-and-error learning. Visual and structured learning materials (such as blackboards, tables, and printed notes) help reinforce concepts.
Turkey: Hands-on, interactive methods are preferred, including peer-to-peer learning and video-based instruction. Seniors also benefit from structured learning goals to stay motivated.
Italy: Face-to-face learning, practical exercises, and video tutorials are the most effective. Seniors favour cooperation over individualism and need structured, goal-oriented teaching.
Austria: Confidence-building techniques and intergenerational learning are crucial in keeping seniors engaged.
Best Practices Across Countries
Group learning and peer-to-peer support foster collaboration.
Face-to-face teaching is essential for building trust.
Simple and clear instructions make learning accessible.
Practical tasks and real-life applications boost motivation.
Structured lessons with well-defined goals help maintain engagement.
Poland (PSP & IFAE): Learning materials should be clear, visually accessible, and well-structured. Printed notes, booklets, and handouts should accompany lessons. Seniors prefer no formal grading, tests, or learning for self-development rather than certification.
Turkey: Printouts, videos, and slides are preferred. Learning materials should be designed for repetition and gradual skill-building.
Italy: Materials must meet accessibility standards (e.g., Verdana font size 14+, line spacing 1.5+). Short sentences and clear explanations reduce cognitive overload.
Austria: Various media formats, including interactive elements, printed resources, and hands-on workshops, are recommended.
Best Practices Across Countries
Use large fonts and high-contrast materials for readability.
Provide printed resources (booklets, summary sheets) for reference.
Keep explanations short and clear to aid comprehension.
Ensure accessibility standards for digital content.
Offer structured, progressive learning materials to build skills step by step.
Poland (PSP & IFAE): Short lessons (1–1.5 hours) with frequent breaks work best. Educators should ensure clear objectives, flexible lesson plans, and plenty of time for questions and discussions.
Turkey: Practical exercises should be repeated at home to reinforce learning. Group projects and intergenerational learning can increase engagement.
Italy: In-person sessions should focus on skill acquisition and social interaction, while online learning should reinforce concepts. Sessions should be limited to 45–60 minutes to prevent fatigue.
Austria: Confidence-building is essential; educators should encourage mistake-making as part of the learning process and use multimodal teaching approaches.
Best Practices Across Countries
Short, well-structured lessons with frequent breaks.
A combination of in-person and online learning is needed to reinforce skills.
Encouraging independent practice at home.
Providing social interaction opportunities to prevent isolation.
Building confidence and motivation by creating a supportive environment.
5. Addressing Challenges and Fears in Senior Learning
Common Challenges Across Countries
Technological barriers: Seniors struggle with complex interfaces, small fonts, and unfamiliar digital tools.
Fear of making mistakes: Many older adults hesitate to engage due to self-doubt and lack of confidence.
Memory and cognitive difficulties: Forgetfulness and slower information processing require repetition and simplified learning materials.
Social and cultural barriers: Some learners struggle with modern terminology or topics like multiculturalism or digital privacy.
Country-Based Overview
Poland (PSP & IFAE): Educators should provide active listening, personalized support, and clear communication. Engaging workshops help build confidence.
Turkey: Seniors need step-by-step guidance and supportive learning environments to reduce fear. Group-based learning helps prevent individual frustration.
Italy: Educators must be patient and encouraging, addressing fears of judgment and failure. Lessons should connect to personal experiences to make learning more relatable.
Austria: Seniors should be encouraged to embrace mistakes and view learning as a process. Intergenerational exchange can help build confidence.
Best Practices Across Countries
Create a safe, non-judgmental learning environment.
Encourage mistake-making as part of learning.
Provide step-by-step support to overcome technological barriers.
Use engaging and interactive teaching strategies.
Relate lessons to real-life experiences to increase motivation.
Poland (PSP & IFAE): PowerPoint, Mentimeter, Moodle, and social media are useful, but many seniors struggle with basic tech navigation. Fake news awareness and web security are crucial components of digital education.
Turkey: Seniors prefer printed materials but are also interested in social media and digital apps. Gamification and interactive tasks can improve engagement.
Italy: Tools like Google Translate, WhatsApp, and Facebook are widely used, but clear learning objectives are essential to prevent frustration.
Austria: Multimedia resources and hands-on practice are key. AI-generated fake content is becoming harder to detect, requiring strong digital literacy training.
Best Practices Across Countries
Simplify digital interfaces and use large fonts/icons.
Teach cybersecurity and critical thinking skills.
Incorporate gamification and interactive tasks.
Use familiar platforms like Facebook and WhatsApp.
Provide continuous guidance and reinforcement exercises.
The spread of disinformation and misinformation poses risks to democracy, public health, and social cohesion, particularly affecting older adults who often lack adequate media literacy. The BonJour project aims to bridge this gap by enhancing media literacy, journalism skills, and digital competencies for people over 55, fostering their social activism, and reducing the generational digital divide through blended learning formats.
Project number: 2023-1-IT02-KA220-ADU-000160320
Webpage: www.bonjour-project.eu/
This survey assesses the ability to remember information, which is the first and lowest level of Bloom’s Taxonomy – a framework for classifying educational learning objectives. Bloom’s Taxonomy consists of six levels: Remember, Understand, Apply, Analyse, Evaluate, and Create. Each level represents a step toward deeper learning and critical thinking.
At the “Remember” level, learners are expected to recall facts, concepts, and key information. This is essential for building knowledge and serves as the foundation for higher-order thinking. Our survey focuses on how well participants remember information after reading, specifically in three areas:
R5: Ability to recall key ideas from a text after reading.
R15: Ability to remember previously read information when needed.
R19: General recollection of what was learned in school.
This is the graphic visualisation of the questions addressing “Remember” (From Bloom’s taxonomy).
Summary of Results
R5 – Recalling Key Ideas After Reading
A large majority (24 out of 28 respondents) agreed or fully agreed that they can recall key ideas from a text.
Only 4 respondents were neutral, and none disagreed.
This suggests that most participants feel confident in remembering key ideas after reading.
R15 – Remembering Information When Needed
23 out of 28 respondents expressed agreement or full agreement with this statement.
7 respondents were neutral, and only 1 showed slight disagreement.
This indicates that most participants can recall information when necessary, though some may find it challenging.
R19 – Remembering School Learning
Responses were more varied, with only 3 people agreeing or fully agreeing that they remember much from school.
13 respondents were neutral, while 15 expressed some level of disagreement.
This suggests that many people struggle to remember school content, possibly due to time passed or lack of relevance in daily life.
Key Insights
Respondents generally feel confident in recalling information immediately after reading and when needed.
Long-term memory of school learning appears weaker, with many either neutral or disagreeing.
No strong disagreement was recorded for short-term recall (R5 and R15), reinforcing the idea that reading helps with retention in the short term.
Diese Umfrage bewertet die Fähigkeit, sich an Informationen zu erinnern, was die erste und niedrigste Stufe der Bloom’schen Taxonomie ist – ein Rahmenwerk zur Klassifizierung von Bildungszielen. Bloom’s Taxonomie besteht aus sechs Stufen: Erinnern, Verstehen, Anwenden, Analysieren, Bewerten und Erstellen. Jede Stufe stellt einen Schritt zu tieferem Lernen und kritischem Denken dar.
Auf der “Erinnern”-Stufe wird von Lernenden erwartet, dass sie Fakten, Konzepte und Schlüsselinformationen abrufen können. Dies ist entscheidend für den Wissensaufbau und dient als Grundlage für höheres Denken. Unsere Umfrage konzentriert sich darauf, wie gut sich die Teilnehmenden nach dem Lesen an Informationen erinnern, insbesondere in drei Bereichen:
R5: Fähigkeit, nach dem Lesen eines Textes zentrale Ideen zu erinnern.
R15: Fähigkeit, sich bei Bedarf an zuvor gelesene Informationen zu erinnern.
R19: Allgemeine Erinnerung an in der Schule gelerntes Wissen.
Dies ist die grafische Darstellung der Fragen zur Stufe “Erinnern” (nach Bloom’s Taxonomie).
Zusammenfassung der Ergebnisse
R5 – Erinnern zentraler Ideen nach dem Lesen
Eine große Mehrheit (24 von 28 Teilnehmenden) stimmte zu oder stimmte vollständig zu, dass sie sich nach dem Lesen an zentrale Ideen erinnern können.
Nur 4 Teilnehmende waren neutral, und niemand widersprach.
Dies deutet darauf hin, dass die meisten Teilnehmenden sich nach dem Lesen sicher an zentrale Ideen erinnern können.
R15 – Erinnern von Informationen bei Bedarf
23 von 28 Teilnehmenden stimmten zu oder stimmten vollständig zu.
7 Teilnehmende waren neutral, und nur 1 äußerte leichte Ablehnung.
Dies zeigt, dass die meisten Teilnehmenden sich bei Bedarf an Informationen erinnern können, obwohl einige dies als schwierig empfinden.
R19 – Erinnern von Schulwissen
Die Antworten waren hier vielfältiger. Nur 3 Personen stimmten zu oder vollständig zu, dass sie sich an viel aus der Schule erinnern.
13 Teilnehmende waren neutral, während 15 in gewissem Maße widersprachen.
Dies zeigt, dass viele Schwierigkeiten haben, sich an Schulwissen zu erinnern, möglicherweise aufgrund der Zeit, die vergangen ist, oder weil es im Alltag nicht relevant ist.
Zentrale Erkenntnisse
Die Teilnehmenden fühlen sich sicher darin, sich direkt nach dem Lesen und bei Bedarf an Informationen zu erinnern.
Die langfristige Erinnerung an Schulwissen erscheint schwächer, viele waren neutral oder stimmten nicht zu.
Keine starke Ablehnung wurde für das kurzfristige Erinnern (R5 und R15) verzeichnet, was darauf hinweist, dass das Lesen das Behalten von Informationen kurzfristig unterstützt.
