Comment by wslh

Another limitation of LLMs lies in their inability to stay in sync with novel topics or recently introduced methods, especially when these are not yet part of their training data or can't be inferred from existing patterns.

It's important to remember that these models depend not only on ML breakthroughs but also on the breadth and freshness of the data used to train them.

That said, the "next-door" model could very well incorporate lessons from the recent Cloudflare OAuth Library issues, thanks to the ongoing discussions and community problem-solving efforts.