this week on the Backtable Podcast.

There have been some papers recently that have shown that, you know, the large language models that are like Claude, GPT, Gemini, they're actually better at making clinical decisions than the clinical AIs, like, you know, Open Evidence and the Doximity AI.

So I think we have to be really careful and recognize that the large tech companies will always have more money than the clinical AI companies.

At least as of right now, I just don't trust any of them to kind of do that work for me without doing my own backup research afterwards.

So it's a lot of like querying to kind of narrow the search and then doing a broader search of the literature to make sure that it's accurate.

Greg, welcome to the show.

Thanks for being here.

Like what do you, what do you envision?