this post was submitted on 24 Jan 2025
67 points (98.6% liked)

Futurology

1943 readers
77 users here now

founded 2 years ago
MODERATORS
voidx@futurology.today
Lugh@futurology.today
Espiritdescali@futurology.today
AwesomeLowlander@futurology.today
67
When AI is tested on questions it can't model from pre-existing answers on the internet, it only scores 10% in the test. (qz.com)
submitted 1 week ago by Lugh@futurology.today to c/futurology@futurology.today
13 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] Lugh@futurology.today 2 points 6 days ago

I think the easiest way to explain this, is to say they are testing the ability to reason your way to an answer, to a question so unique, that it doesn't exist anywhere on the internet.