News for hackers. Stuff that matters.

A comment on MCP Run Python. Parent comment

Re:MCP Run Python by simonw on Thursday April 17, 2025 @02:16PM (#43720399)
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.
[ Parent | on HN ]
Re:MCP Run Python by jamestimmins on Thursday April 17, 2025 @05:18PM (#43722315)
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.
[ Parent | on HN ]
Re:MCP Run Python by fzzzy on Friday April 18, 2025 @08:10AM (#43727310)
I think this is inevitable. Whatever is most highly represented (correctly) will become even more dominant.
[ Parent | on HN ]
Re:MCP Run Python by __mharrison__ on Thursday April 17, 2025 @05:33PM (#43722467)
So that's why it writes such bad pandas code...
[ Parent | on HN ]