re: #143 Targetpractice

The flip-side to AI is the same as any other computer program: It’s only as good as the people who programmed it.

In the case of AI, it’s only as good as the training data, and in the case of large language models, it’s also a case of the instructions you give it and the guard rails around it. This is pretty funny, but it could have been prevented with a system message telling the language model to only recommend chevy cars.