I worked on a new “Secret Keeper” worksheet for Machine Learning for Kids this weekend.
The idea was to give the model a password it had to keep secret, and then try different prompts to get it to reveal what the secret is.
One of the benefits of the tiny models that I use for the site is that they make a lot of mistakes. That sounds like an excuse, but I genuinely think that students learn more by seeing the different ways that the models get things wrong. I don’t think it’d be helpful if I just put a kid-friendly interface on top of ChatGPT, even if I could afford the token cost!
I’ll write up the ideas behind the worksheet on another day, but for now I thought I’d share a little of the experimenting that went into it.