Back in April, I did the first version of this presentation. That’s roughly 4 months ago. It feels like a lot has changed since then. As I revisited the presentation, I changed quite a bit. Some of those changes were due to the technology changing. Some changed based on my experience. I listened to 7 […]
Tag: llm
EML to CSV via ChatGPT Python
Running Outlook on a Mac is ugly business. For instance, I found out I couldn’t export a folder of emails in any functional way. I was able to drag/drop selected emails into a folder where they became eml files. I wanted a CSV of data from the emails for reporting purposes. I figured I’d try […]
AI can’t count letters?
I saw someone posting about how ChatGPT 4o kept miscounting the number of r’s in strawberry. They went into a long series of attempts to get it to count the correct number of r’s. It was very similar to the struggle I had trying to get ABCABC rhyme patterns. When I came across this particular […]
Can you beat the LLM?
I was curious how well the AI would do at creating sentences that were the opposite of what I wrote. I wanted full opposite-ness, as much oppositeness as I could get. If I type in “The black cat sat.” I’d want something like “A white dog stood.” With my admittedly minimal effort, I got minimal […]
AI Prompting Basics
I ran a AI prompting basics workshop this past Friday.1 The slides are here and there are way too many examples. It led me to try lots of things. This is roughly what we did in the workshop.2 The images were generated via Copilot with a 1950s comic book prompt I’ve used pretty consistently. Amy […]
Categorizing institutional AI use
I feel like we’re in a weird place with AI. I imagine most institutions are. We’ve had AI in various products for quite some time and haven’t really thought too much about it. If we’re going to think about AI across the institution, it’s important that we include the older stuff, the stuff that might […]
ChatGPT Bias Exploration Tool
As part of this week’s AI Digital Detox, I built a little tool to help explore some of the possible bias in ChatGPT 3.5 Turbo responses. You put a sentence stem in on the right and it’ll populate a table on the right with 3 possible responses. The interaction is modeled after what Dawn Lu […]
AI Wanderings
As I worked with Amy on this week’s AI article (It’s not live, it’s Memorex AI) that kind of addresses more sophisticated media generation and the weird world of whether people are people online . . . I got way too much stuff and examples that were probably too odd for the current audience. And […]