this post was submitted on 27 Jan 2024
12 points (77.3% liked)

Futurology

3250 readers
63 users here now

founded 2 years ago
MODERATORS
voidx
Lugh
Espiritdescali
AwesomeLowlander
12
Two-faced AI language models learn to hide deception - ‘Sleeper agents’ seem benign during testing but behave differently once deployed. And methods to stop them aren’t working. (www.nature.com)
submitted 2 years ago by Lugh to c/futurology
9 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] possiblylinux127@lemmy.zip 1 points 2 years ago (1 children)

Sorry, to late for that

[–] mateomaui@reddthat.com 2 points 2 years ago (1 children)

Alright, I’ll be out back digging the bomb shelter.

[–] possiblylinux127@lemmy.zip 1 points 2 years ago* (last edited 2 years ago) (1 children)

Its too late for that honestly

[–] mateomaui@reddthat.com 2 points 2 years ago

Alright, I’ll switch to digging holes for the family burial ground.