this post was submitted on 20 Mar 2025
43 points (100.0% liked)

Artificial Intelligence

207 readers
32 users here now

Chat about and share AI stuff

founded 2 years ago
MODERATORS
[email protected]
43
Punishing AI doesn't stop it from lying and cheating — it just makes it hide better, study shows (www.livescience.com)
submitted 2 weeks ago by [email protected] to c/[email protected]
11 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 1 points 2 weeks ago* (last edited 2 weeks ago)

isn't this kind of the whole point of how GANs are trained? Except in this case the adversary is yourself instead of a different net