Architecture: Dome Home by a Frank Lloyd Wright Apprentice

 A Sunflower-Inspired Dome Home by a Frank Lloyd Wright Apprentice Asks $450K - Dwell

AI: is ChatGPT generated code good?

useful as "copilot", not as a "pilot"

ChatGPT Code: Is the AI Actually Good At Writing Code? - IEEE Spectrum

Overall, ChatGPT was fairly good at solving problems in the different coding languages—but especially when attempting to solve coding problems that existed on LeetCode before 2021. For instance, it was able to produce functional code for easy, medium, and hard problems with success rates of about 89, 71, and 40 percent, respectively.

“ChatGPT may generate incorrect code because it does not understand the meaning of algorithm problems, thus, this simple error feedback information is not enough,” Tang explains.

While ChatGPT was good at fixing compiling errors, it generally was not good at correcting its own mistakes.

The researchers also found that ChatGPT-generated code did have a fair amount of vulnerabilities