“Everybody’s talking about AI!” This week’s joke is that the US Education Secretary spoke enthusiastically about the introduction of A1 into early schooling. A1 is a brown sauce, similar to HP sauce in the UK. Contrarily, the Stanford AI Index 2025 Annual Report shows that people are now more aware of AI, particularly large language…More
Tag Archives: architecture
Evidence and absurdity
In the previous posts I recalled five categories of design explanation. I used the innocuous example of deciding to insert a large window into a living room. I explored how a client/reader might regard various explanations as either sensible or absurd. I wanted to avoid the language of truth and falsity, arguing that decisions and…More
Explain this …
In my previous post I explored how LLMs provide explanations of the “reasoning” by which they produce their outcomes (i.e. responses, answers, decisions). At least in their current iteration, platforms such as ChatGPT are tuned to generate an explanation independently of the process by which they came up with their response in the first place.…More
The meta-reasoning illusion
The ability of an LLM to provide an account of the processes by which it came up with its results, as in the inventory table I showed in the last posting, is indeed convincing. But apparently it is an “illusion.” I can’t yet find an article on the subject, so I have come to rely…More
Inferring a book from its index
I’m busy creating the index for my current Routledge book: AI and Language in the Urban Context: Conversational Artificial Intelligence in Cities. As yet I have had little success in deploying AI to create an index for me. ChatGPT will however create a book proposal from an index. It seems that ChatGPT called on assistance…More
The Quid Pro Coaster
Designers, writers, and illustrators in general are skilled at drawing inspiration from just about any source. As I have shown in previous posts, LLMs seem capable of something similar, especially with source texts that are colourful, include spatial cues, characters, situations and accounts of interesting experiences. But how do they handle dull, prosaic, non-spatial texts,…More
From text to image via LLM
Text and writing are important components in creating architecture. To put it more strongly: text is deeply intertwined with the production of architecture, serving as more than a mere communication tool. Text impacts design thinking, theory, history, and the way the built environment is constructed — materially. As in my previous posts, I’m seeding this…More
Share your expertise
Google’s NotebookLM utilizes the RAG methodology for document interrogation, allowing users to gain insights from multiple texts simultaneously, while the University of Edinburgh has introduced its ELM built on ChatGPT for educational use. Both tools enhance understanding in specialized fields by enabling easy document uploads and tailored responses, benefiting users in architecture, law, and healthcare.More
AI scripts a debate about urban glare
I’m testing the ability of large language models (LLMs), like ChatGPT, to conduct AI to AI conversations that in some way parallel how two people might work through a problem together. I’ve discovered that it’s not necessary to contrive a condition where two AIs talk to each other as in my previous post, or where…More
From CAD to AI
The complex relationship between cybernetics and semiotics outlined in previous posts helps me at least identify major differences in thinking about cities, and the lack of comprehension by adherents to one with the other. In part it’s a distinction between a calculative approach to cities, and a more humanistic orientation, and by “humanistic” I mean…More