Easy Wins
This blog celebrates easy wins with large language models (LLMs) and other things I find interesting. I cross post my blog entries to LinkedIn and X, where I’d love to interact with you in the replies and comments.
-
AI is Really DIY
Read more: AI is Really DIYI’m sorry the robot dog isn’t wearing pants. I told Grok I needed a robot dog wearing a DIY (“Do It Yourself”) shirt. It gave me exactly what I asked for. That’s how the image creation models work. The picture passed all the classifiers I specified. It didn’t think to ask me if the dog…
-
How “AI” Image Generators Work
Read more: How “AI” Image Generators WorkI’m writing this article to help artists and users understand what the current crop of AI image generators work do and how they work. I won’t dive into technical details. This explanation is “right enough” for a 5,000 foot discussion of how to work with the technology and address high level concerns, such as whether…
-
When Trust is the Negative Space of Distrust
Read more: When Trust is the Negative Space of DistrustIn this article, I explore how trust is often measured as the lack of distrust. I draw an analogy with drawing, and call trust the negative space of distrust.
-
LLMs are Bad at Facts but Good at Knowledge
Read more: LLMs are Bad at Facts but Good at KnowledgeDo you know the difference between facts and knowledge? Did you know there is a difference? Let’s explore that and how it applies to using LLMs.