Hacker News Reader

I think it's more about tapping into the Jupyter ecosystem of visualization libraries etc, plus the fact that there's lots of data analyst examples in the training data that come from notebooks.

View on HN

That's an interesting dynamic of the training data impacting the architecture. I wonder if this is a one-off or we see that in other areas as well.

I think this is inevitable. Whatever is most highly represented (correctly) will become even more dominant.

So that's why it writes such bad pandas code...

Reply on news.ycombinator.com