• 0 Posts
  • 17 Comments
Joined 1 year ago
cake
Cake day: January 19th, 2024

help-circle


  • This is not a good quality article from the point of statistics.

    The main statistical claim is that OE fails 9% of the times on USMLE. If you want to form a reasonable conclusion from that you need to compare it to control. The control here would be the fail rate of an average doctor. Or to be frank maybe better control would be the fail rate of a bad doctor because if OE beats that then there is an arguement to be made that there are people who OE could help.

    Passing grade os USMLE Clinical Knowledge exam is 214/300 and mean score is 246. Idk the specific scoring but if it is scored the usual way then I believe this article is overly dramatic














  • The correct usage of LLMs in coding imo is for a single use case at a time, building up to what you need from scratch. It requires skill both in talking to AI for it to give you what you want, knowing how to build up to it, reading the code it spits out so that you know when it goes south and the skill of actually knowing how to build the bigger picture software from little pieces but if you are an intermediate dev who is stuck on something it is a great help.

    That or for rubber ducky debugging, it s also great in that