“Now, what that meant was Matt asking his large language model for a one or two page story about the student as a garbage truck. And he added prompts for comprehension questions.”

“What we tried to do is, you know, using large language models and AI, we tried to really ground probability of success in an empiric data set, where we use Bayesian statistics.”

“If you can get that information and you can turn that unstructured data into semi-structured data and connect it to the prediction, then you can use the storytelling power of the large language models”

“We had two drivers per every vehicle. So, again, there was just like this massive explosion. It was an owner-operator model where we didn't have as many company trucks that we had to invest into. But they were bringing their own trucks on with us.”

“And the newer large language models are really able to handle context much better. So we're getting much richer data out of that free text within the electronic medical record.”