Post #4036404
2026-07-21 11:14 UTC
@paka@mastodon.scot @fallenhitokiri@social.screamingatmyscreen.com Seems like a bad study if only 44% can get it correct with or without LLMs. Especially if you tell them to use a bad model you know will fail on subjects they know nothing about. Paying them incentivized them to care slightly more but clearly not enough to abandon the tool you asked them to use. 😬
Replies (2)
-
@fallenhitokiri@social.screamingatmyscreen.com 2026-07-21 11:48
@webology@mastodon.social @paka@mastodon.scot the study IMHO highlights how much narrative vs actual research happens on both sides.
-
@saladshootrdlux@mastodon.social 2026-07-21 15:44
@webology@mastodon.social @paka@mastodon.scot @fallenhitokiri@social.screamingatmyscreen.com this was my thought as well, seems like the study set subjects up to fail if they used AI. confidence in AI is interesting, but so is confidence in the study. maybe it says more about a subject’s ability to discern AI models than anything else.