this post was submitted on 01 Dec 2024
46 points (88.3% liked)

Futurology

3156 readers
19 users here now

founded 2 years ago
MODERATORS
voidx@futurology.today
Lugh@futurology.today
Espiritdescali@futurology.today
AwesomeLowlander@futurology.today
46
Multiple LLMs voting together on content validation catch each other’s mistakes to achieve 95.6% accuracy. (arxiv.org)
submitted 8 months ago by Lugh@futurology.today to c/futurology@futurology.today
25 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] copygirl@lemmy.blahaj.zone 8 points 8 months ago

I would not accept a calculator being wrong even 1% of the time.

AI should be held to a higher standard than "it's on average correct more often than a human".