In December, I published the first-ever architecture interview with a bot . Ammaar Reshi on Twitter inspired the idea by publishing a children’s book co-written and illustrated by AI after experimenting with ChatGPT and MidJourney over the course of a single weekend. Since most groundbreaking technologies pass by our lives without even noticing, Reshi’s simple but powerful example illustrates how 2022 might be remembered as the year when AI-fueled tools finally become accessible to a larger audience: from text-to-image generation Stable Diffusion, Midjourney, and DALL-E 2, to the surprisingly smart OpenGPT, a language-processing designed artificial intelligence (AI) capable of generating human-like text.

It’s common knowledge that architects often resist incorporating state-of-the-art technologies: it has been happening with this new wave of tools, but it also occurred with the widespread use of hyper realistic renderings and 3D models. Before that, it happened with Photoshop. Before that, AutoCAD and Revit. Before that, computers at large. And before that, photography. The list goes on and on.

As a symbol of what machine learning could achieve in the short term for architecture and humankind, I “talked” with OpenGPT about the architecture trends of 2023, and I would like to share a few reflections.

Where ChatGPT Gets Its Knowledge

The two sessions conducted were held on December 18 and 19; the original conversation with ChatGPT extends to approximately 6,000 words. The bot might recall and reference statements made during the current session, but is unable to quote from previous conversations and does not have access to the Internet, as it explained on its own:

ChatGPT: “As a language model, I was trained on a large dataset of text from the internet and other sources. This training allows me to generate responses to a wide variety of questions and topics based on the patterns and relationships present in the data […] My knowledge and responses are based on the state of the world at the time of my training, and I do not have the ability to update or expand upon that knowledge.”

At the time of writing, ChatGPT’s latest stage of training had been completed in 2021; thus it doesn’t know, for example, anything about the World Cup in Qatar.

How Could ChatGPT Predict the Architecture Trends of 2023?

First of all, any prediction, conducted either by humans or robots, is an extrapolation of current, predictable events — events or tendencies that can intensify, soften, or even disappear. Predictions are, despite their purpose, quite predictable. Hardly any forecast for 2020 New Year’s Eve mentioned a pandemic or a full-scale Russian invasion of Europe territory in the 2022 edition. Forecastings express a stakeholder’s desires (and fears) more than anything else; for example, a Metaverse pundit would seldom describe a future without its field of expertise as part of it.

Ultimately, the future is always one step ahead of us.

What amazes me the most is that ChatGPT aims to “provide conversational answers to users’ queries” based on an extensive up-to-2021 database, but the quality and precision of its responses lead to thinking that ChatGPT could work as a crystal ball as well.

The logic could be: “If it’s smart enough to know almost everything about both the past and the present, it could be smart enough to create a forecast of the future.” At least, that’s the logic we apply with humans.

Having said that, architecture is a slow-cooked discipline: a built project seldom takes less than a year or two from the initial design phase to the final construction and opening. Therefore, architectural trends may not change significantly from year to year, but there are rising factors or variables that might be considered in the future when designing, analyzing, or evaluating the built environment. In fact, critical writing, ephemeral architecture, media, photography, performance, and architectural theory can test, adopt, or question these movements. ChatGPT seems to agree with me:

Nicolas Valencia: “[…] architecture is quite slow when it comes to embracing new trends.”

ChatGPT: “It is true that the field of architecture tends to evolve relatively slowly, and new trends and technologies may take time to be adopted and integrated into practice. However, it is important to keep in mind that the pace of change can vary widely depending on the specific area of architecture being considered and the specific context in which it is being applied.”

An Unexpected Challenge: Editing a Bot’s Responses

I had a great time chatting with ChatGPT, but when I went to edit the conversation for the article, I realized it was challenging to edit the bot’s responses without introducing (human) bias. ChatGPT might have solid answers, but it’s up to the human editor how they would finally be represented in any article.

In my experience, ChatGPT’s answers were Solomonic every time I asked for a deepening of its trends forecast. Here’s an example that didn’t make it into the final version of the piece published on ArchDaily.

Nicolas Valencia: “LEED certification has been discredited since it focuses ‘overwhelmingly on operational emissions rather than emissions from the construction supply chain,’ as expressed by Architects Declare member Andrew Waugh.”

ChatGPT: “It’s true that the LEED certification program, which is administered by the U.S. Green Building Council (USGBC), has come under criticism in the past for focusing more on operational emissions rather than emissions from the construction supply chain. However, it’s worth noting that LEED has evolved over time and now includes credits for a wide range of sustainability factors, including materials and resources, indoor environmental quality, and innovation in design.”

It’s important to recognize that no single rating system or certification program is perfect, and it’s always a good idea to do your own research and due diligence when evaluating the environmental performance of a building or product. However, LEED and other similar programs can still be useful tools for evaluating and improving the sustainability of buildings and construction projects.

ChatGPT’s cagey answer can be narrowed down to the following strategy: 

• First, acknowledge the shortcomings of LEED certification.
• Second, explain how the certification has evolved by embodying the criticism.
• Later, recognize that “no single rating system or certification program is perfect.”
• Finally, admit that those programs “can still be useful tools.”

This sounds as practiced and polished as a response from a politician. Afterward, when asked its opinion on automation in architecture, ChatGPT replied:

It’s important to approach automation and other forms of technology in the architecture industry with a balanced perspective, recognizing both the potential benefits and potential drawbacks.

This response structure repeats throughout the conversation on diverse topics, but the latest quote encapsulates what ChatGPT tries to answer when I asked for a personal opinion: “a balanced perspective, recognizing both the potential benefits and potential drawbacks.”

Of course, what balanced means isn’t unbiased. Thus, as a human editor, I had to preserve the bot’s intended meaning when editing its answers. In addition, I may need to include an Editor’s Note to ensure that readers do not misunderstand formatting such as hyperlinks or italicized or bold text as being decisions made by the bot: “The following conversation has been edited for length and clarity. Hyperlinks and stylizing have been added by humans.”

ChatGPT Holds No Opinion on Architectural Projects But Synthesizes What Humans Have Previously Said

To be honest, the 2023 architecture trends brought up by ChatGPT remind me of actual forecasts published in 2021, 2020, and 2018. This is not surprising, since the model has read millions of websites under the supervision of humans — using a technique called Reinforcement Learning from Human Feedback (RLHF) — in order to create a human-like written answer, not to develop critical thinking.

Thinking like an architecture critic, or critical thinking in general, is not a strength of ChatGPT. (At least, not yet.) 

For example, I asked it to “show [me] an example of a good architectural project.” Its answer was Jørn Utzon’s Sydney Opera House, “a multi-venue performing arts center that is considered a masterpiece of modern architecture” … by humans, not based on its own judgment.

Similarly, despite the subjective nature of their overall quality, when asked for examples of biophilic design, ChatGPT mentioned the Singapore Botanic Gardens and the New York Times Building because both projects “feature a range of biophilic design elements.”

ChatGPT has read a lot about architecture and provides examples when being asked for a specific topic, but this confirms that the bot is able to provide information and examples based on the descriptions it has read, rather than providing its own aesthetic analysis.

Due to the high speed of AI development, this interview might become outdated sooner rather than later. In fact, OpenAI CEO Sam Altman humbly described ChatGPT — its own product — as “incredibly limited,” but “it’s a preview of progress.” Therefore, the architecture trends described by the chatbot should be taken with a grain of salt, but for the purpose of the interview, it’s a sneak peek of what artificial intelligence could achieve in the short term for architecture and humankind.

From a Luddite perspective, the current AI disruption could mean the definitive obsolescence of (human) architects, embodying a fear that has always floated around over the last two centuries: humankind losing the exclusive ownership of creativity—despite how uncreative mainstream architecture and urban planning have become worldwide already.

From a (scarce-than-ever) optimistic approach, AI could wipe out a bulk of boring processes and ungrateful job positions in architecture so that practitioners can focus on more rewarding tasks when it comes to analyzing, designing, and building the architecture of the future. The price might be the shrinking of firms’to just a few people or deepening the specification and technical-focused of job roles within our industry. (How many architects actually design a building today?)

Regardless of which path things lean toward, technological revolutions can’t be treated as inevitable, like a ship reaching a cascade. Humans will eventually have something to say and to do. 

This text is an edited and slightly expanded version of an essay originally published by the author on Medium.