Science Surf
But let your communication be Yea, yea; Nay, nay.
For whatsoever is more than these cometh of evil.
Search

Primary Menu

Skip to content
Allergy, Software

A useless study of AI accuracy

31.03.2025 admin
https://www.jaci-inpractice.org/article/S2213-2198(25)00280-6/pdf

Although promised, the supplement with the questions is missing and there is no information in the methods how the authors prompted – so basically useless as methods cannot be replicated.

And at the end, chatGPT is only a mirror of how good or bad these experts informed the public…

 

CC-BY-NC Science Surf , accessed 23.07.2026
aiallergy

Post navigation

Previous PostI asked chatGPT about SARS-CoV-2 genome similarities and this is what I gotNext PostCochrane: Aprilscherz ja oder nein?

About

A science blog since 2006
Staying on top of the wave
Non-profit, no cookies, no ads
AI content is labelled

Impressum

Feed

RSS

Last Changes

  • Wissenschaftsrat fordert intellektuelle Souveränität
  • The biggest turning point in medical science that I have ever encountered
  • Withstand the threshold
  • Is peer review overrated? Are journals superfluous?
  • How to interpret an odds ratio of less than 1
  • Zur Katherina Reiche Diskussion - müssen KI Beiträge gekennzeichnet werden?
  • Farm dust and immune readouts
  • The Südhof Nomenclature
  • Markus Blume und die künstliche Intelligenz
  • A bookmarklet that highlights AI generated prose
  • Datenschutz in Bayern
  • Ralf Frisch und sein "Fuck you Greta" Artikel auf Zeitzeichen
  • Double blind peer review - well-intentioned but too many side effects
  • 250€ per review
  • AI is killing humans

Search

Impressum Proudly powered by WordPress