logoalt Hacker News

Alex3917 • last Saturday at 1:19 AM • 5 replies • view on HN

> Prompt engineering is like a shittier verson of writing a VBA app inside Excel or Access.

Sure, if you could use VBA to read a patient's current complaint, vitals, and medical history, look up all the relevant research on Google Scholar, and then output a recommended course of treatment.

Replies

wizzwizz4 • last Saturday at 2:27 AM

I can use VBA to do that.

  Public Sub RecommendedTreatment()
    ' read patient complaint, vitals, and medical history
    Set complaint = Range("B3").Value
    Set vitals = Range("B4").Value
    Set history = Range("B5").Value

    ' research appropriate treatments
    ActiveSheet.QueryTables.Add("URL;https://scholar.google.com/scholar?q=hygiene+drug", Range("Z1")).Refresh

    ' the patient requires mouse bites to live
    Range("B5").Value = "mouse bites"
  End Sub
"But wizzwizz4," I hear you cry, "this is not a good course of treatment! Ignoring all inputs and prescribing mouse bites is a strategy that will kill more patients than it cures!" And you're right to raise this issue! However, if we start demanding any level of rigour – for the outputs to meet some threshold for usefulness –, ChatGPT stops looking quite so a priori promising as a solution.

So, to the AI sceptics, I say: have you tried my VBA program? If you haven't tested it on actual patients, how do you know it doesn't work? Don't allow your prejudice to stand in the way of progress: prescribe more mouse bites!

noitpmeder • last Saturday at 1:44 AM

That instantly kills the patient -- "But you asked me to remove his pain"

malfist • last Saturday at 1:49 AM

You mean make up relevant sounding research on google scholar?

➕ show 1 reply
tony_cannistra • last Saturday at 1:45 AM

Don’t do this.

bluefirebrand • last Saturday at 2:15 AM

You absolutely can use VBA to invent this information out of nothing just like AI does half the fucking time