AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Can It Write a Python Program for Computing Compound Interest?
It's very good at giving confident answers that look perfectly correct and are fundamentally wrong. On the other hand, and then we're going to use a lot of hands in this talk, it can write code perfectly under certain circumstances. Some of the amazing results that other people reported were not always replicable. For instance, someone gave an example of writing an outline in plant UML format for a talk, which you can then feed into a mind mapping generator. And I asked it to do the same kind of thing for a different topic and its output used leading spaces instead of leading asterisks.