this post was submitted on 31 Jul 2025
164 points (96.1% liked)

Facepalm

3352 readers
5 users here now

founded 2 years ago
MODERATORS
irelephant@lemmy.world
Irelephant@lemm.ee
The_Picard_Maneuver@lemmy.world
irelephant@lemmy.dbzer0.com
164
AI is like that friend who will never tell you that you're actually in the wrong. (infosec.pub)
submitted 1 week ago by The_Picard_Maneuver@lemmy.world to c/facepalm@lemmy.world
25 comments fedilink hide all child comments
 

This screenshot and similar ones have been circulating with concerns that these chatbots are dangerously sycophantic.

you are viewing a single comment's thread
view the rest of the comments
[–] otacon239@lemmy.world 12 points 1 week ago

This right here. If someone can maliciously make an LLM do this, there are plenty of others out there that will do it unknowingly and take the advice at face value.

It’s a search engine at the end of the day and only knows how to parrot.