this post was submitted on 15 Jan 2025
11 points (92.3% liked)

Futurology

1891 readers
122 users here now

founded 2 years ago
MODERATORS
voidx
Lugh
Espiritdescali
AwesomeLowlander
11
Can AI Be Trusted? The Challenge of Alignment Faking (www.unite.ai)
submitted 2 days ago by Lugh to c/futurology
6 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] Lugh 1 points 2 days ago

Building trustworthy AI won’t be easy, but it’s essential.

It doesn't seem a top priority for most of the people creating AI. I suspect we will mainly be learning from our mistakes here, after they've happened.