A large language model (LLM)-powered systematic review of over 1,000 studies revealed that, despite the growth of medical research involving LLMs, a majority of studies do not involve real-world clinical data.
I hacked car charging to work with my electric bike!
Lors d’un repas entre amis, j’ai posé la question de la référence à 67.
Nos ados ont confirmé utiliser l’expression sans en connaïtre la signification. Mon pote à fond dans l’IA (on en a tous un) a alors demandé à ChatGPT qui lui a répondu que c’était une référence au département du Bas-Rhin issue de la scène rap de cette région.
Je crois que je vais longtemps lui ressortir l’influence mondiale de la scène rap du Bas-Rhin…
Introducing bluffbench, a new tool to evaluate how well LLMs actually see data plots.
When we trick LLMs with secret #RStats transformations, they can miss the visual contradiction.
bluffbench helps us measure this "blind spot" in AI coding agents. Learn more: https://posit.co/blog/introducing-bluffbench/
We got our first review stating that as p-curve was recently criticized, and z-curve was also not 'vetted by a real statistician', the method should not be trusted.
No statistical tool could ever damage science as much as this horrendously flawed authority argument.
Stephen Turner
Matt Gray
James Balamuta
ploum
Posit
Wolfgang Viechtbauer
Daniel Lakens