Post

So this is a fascinating article about how a family used ChatGPT to help (emphasis on *help*, not on doing everything) diagnose the rare genetic disorder their kid had. While I know it will make some people angry, I think there are a few good lessons in here: www.bostonglobe.com/2026/09/12/m...

... to help interpret the results, rather than assuming that the tool replaced the professionals. They still had to deal with some false alarms (though in this case it was because of bad input data, not AI hallucinations), which is why it was useful that the parents were careful.

I think stories like this are helpful in (again) highlighting how the best use of these tools is very much when they're seen as eager research interns. They can gather lots more data and present potentially useful research avenues, but it's up to the humans & experts to then do the real exploration.

Does everybody know you can explicitly tell Claude not to hallucinate? I learned this and gave it these rules months ago, and it’s remarkable how different the results are! www.icloud.com/notes/090yXE... 

If you use AI as a research *assistant*, it's great. If you use it as your primary researcher, it's *terrible*.