Prompt engineering and creativity

Designers typically pride themselves on generating their own ideas. But AI models, such as ChatGTP, can help designers generate ideas through prompt engineering, that is, the process of structuring or crafting an instruction in order to produce better outputs (texts or images) from a generative artificial intelligence (AI) model. This may suggest that designers using prompts for idea generation are becoming editors or curators rather than ideators.That is, designers are selecting, refining and promoting the most promising ideas produced by the algorithms. If so, do designers may risk outsourcing their innate spark of creativity to AI models rather than creating the idea itself. Or, is it the case that prompting is simply unlocking a new form of creativity? After all, prompt engineering is a creative activity in that it means experimenting with different phrasing, structures, or contextual elements in the prompt to get the best possible design output from the AI model. This suggests that prompting enhances rather than diminishes human creativity. But even so, as chatbots become more powerful and accessible, designers need to address concerns about authenticity, quality and ethical standards.

Performative ideation

The concept of performativity* - the symbiotic or interdependent relationship between words and actions -could, in the wider interpretation of practical living and experimenting be applied to design ideation in that generating and communicating ideas have a performative function, that is, designing is essentially about change and changing the world. The overreaching transformative role or function of design means that the workshop participants are agents for change, that is, they are seeking desirable outcomes through design thinking and making. In this performative pursuit, the participants are not so much competing to impress others - "mine idea is better than yours" - but, and more important, to develop designer authenticity and resilience, both collectively, as members of the design community, and individually, in what philosopher Martin Heidegger called our "authentic self".* How To Do Things with Words (Austin 1962) is the foundational text on performative language

Creativity and critical thinking

Creativity and critical thinking are both processes of thought which can be viewed separately - one is expansive, the other reductive - or they can be seen as working together. That is, when designers generate ideas they can either conceptualise something new outside the ordinary, without fear of failure, or make new connections while thinking critically about the ideation process and its outcome, which is critical. That is, creative and critical thinking are not mutually exclusive. But, in practice, critical  thinking is needed to rule out the truly poor or impractical ideas, to produce a workable solution. In this, the designer turns on the inner critic and considers adjustments or alternatives. Moreover, when communicating ideas, the designer, when challenged would allow for feedback in the form of criticism. Being critical, on the other hand, in evaluating ideas, differs from thinking critically in that being critical may suggest a negative attitude, a fault-finding mindset or aversion to risk-taking (negative criticism). Positive criticism, on the other hand, would contribute to how designers understand how creative and critical thinking go hand in hand also raising awereness about personal accountability and wider ideation issues such as ethics and serving the greater good. Ideators, then, at best, are both creative and critical thinkers.

Playfulness and ideation

The ideation workshop embraces the power of playfulness and its creative role in design allowing the participants to follow their curiosity and imagination ("what if ..."). That is, the participants engage in playful thinking and behaviour with the intention to achieve serious objectives, that is, problem-solving. Ideation in this way ("serious play"), is unstructured yet constructive encouraging the participants to think both creatively and critically culminating in representations and presentations of ideas. And not because the participants are following instructions but because the workshop environment and brief invites and facilitates a playful and exploratory mindset. In this, the workshop is inspired by, and builds on pedagogical research* that reflects the workshop as a learning experience through thinking and doing. https://www.sciencedirect.com/science/article/pii/S2666374020300248

Idea et Materia Unum

The workshop reflects ideation as part of everyday, purposeful design activity where, in the process of generating and communicating ideas, idea and matter are one. That is, the idea, as an element of thought becomes matter when the idea, abstract, concrete or visual is explained and presented. In this, the workshop keeps alive the tradition of experiment and the range of materials, new and old, with which the designer works using both analogue and digital tools, from freehand sketching to CAG, that is, whatever works best for the participants. That is, the design task may guide the tool choice but the pick is also a matter of personal preference. This, in turn, reflects how the actualisation of design ideas relies not only on the designer but the commonplace effort of engineers, builders, manufacturers and various skilled trades.

New ways of thinking

'If you want to teach people a new way of thinking, don’t bother trying to teach them. Instead, give them a tool, the use of which will lead to new ways of thinking.' is a quote from Buckminster Fuller, the American designer and innovator (1895-1983). Fuller believed in the power of technology to change society. And so he sought to pursue and develop his ideas for the benefit of everybody. What, then, we may speculate, would Fuller make of GenAI? Fuller said 'the future is anything but defined - it is created by us'. Also, 'the best way to predict the future is to design it'. Fuller again, 'You can't change the way people think, all you can do is give them a tool, the use of which will change their thinking'. And so, it seems, Fuller's notion of a thinking tool is not just about the technology but also the design of the tool. This suggests that Fuller, who described himself as a comprehensive anticipatory design scientist, would take up GenAI as a thinking tool, a tool capable of augmenting design thinking, ideation and innovation. But when asked whether he was bothered by the fact his invention of the geodesic dome was used by the military, Fuller replied: 'How tools are used is not the responsibility of the inventor.' Sources:. https://medium.com/disruptive-design/buckminster-fuller-the-creative-shape-shifter-that-every-change-maker-can-learn-from-a5c4702d644b https://larrygmaguire.com/self-disciplines-buckminster-fuller/  https://lareviewofbooks.org/article/life-verb-applying-buckminster-fuller-21st-century/

Unpredictability and uncertainty

While traditional AI is good at analysing large datasets and predicting typical outcomes, that is, tuned for specific tasks, Large language models, LLMs, used in generative chatbots such as ChatGPT are now big enough to reach beyond the constraints of their training data. As a result, they can display unpredictable behaviours, including AI hallucination. Such behaviour reflects how uncertainty is not only inherent in generative AI systems but also a characteristic of the real world, and increasingly so when the collective knowledge base is unstable and shifting. Ideation is also conditioned by uncertainty or unpredictability. That is, an idea is just a proposal or suggestion which may, or may not be realised. And so, idea communication is aiming at removing as much uncertainty as possible about the idea's realisability. Still the final idea outcome is unpredictable - its uncertainty remains. So what about the strength of generative AI as a tool for ideation? Faced with complex user demands, in sociopolitical, economic and cultural contexts, generative AI cannot deliver certainty in human scenarios that require flexibility beyond its data-driven approach. The answer, then, lies in adaptive human-AI collaboration. For example, designers may use prompt engineering as a guide to LLM responses, an AI technique akin to human step-by-step problem solving.