I'd be curious to know how good of a job Google can do at recognizing content generated by ChatGPT. While I've seen some tools that claim to detect AI-written text, their performance is usually pretty lackluster. Even if they have an internal model which can distinguish ChatGPT-authored content reliably, it seems like it'd be prohibitively expensive to run at scale (on the assumption that it must be a pretty large model to reliably solve a difficult classification problem).