Pragmatism in the real world

Some thoughts on LLM usage in my work

While it would be nice to put the genie back in the bottle, that hasn't happened often in human history, so for the foreseeable future, AI in the form of LLMs are here to stay. I imagine that what we use them for will change over time as we collectively internalise their limitations. Personally, I'm now using them for my work as much as I reasonably can. This is involving many different areas, such as… continue reading.

Generating scripts with LLMs

With the recent release of the new OpenAI ChatGPT that can do image generation, I thought that I might add a feature image to my last blog post. I've had mixed experiences of AI generation of images, probably because I'm not good at prompting them. I started with this: We now have an image, but it doesn't have a credit. Now, I could go back to the LLM and ask it again, but these things… continue reading.