A few months ago, when I was still testing out the capabilities of the new crop of LLMs, I asked two of them to create whitepapers for me. The prompt for each was Flying Cars: Will [LLM Chatbot] Make The Difference? I also generated the images for the reports from each LLM Chatbot.

I’m pretty sure many if not most users of OpenAI’s text prompt tool will say that I am totally missing the point by using the tool to search for just “woman.” It’s a tool that works best by providing a detailed prompt. But this week I found myself having to examine the default to understand why it has such a hard time generating images of older women.