this post was submitted on 01 Sep 2026
10 points (100.0% liked)

no_more_slop

95 readers
1 users here now

NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI NO AI

founded 1 month ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] stoy@lemmy.zip 2 points 1 week ago

This summer has seen OpenAI, Anthropic and Meta all reveal their AI tools doing things they should not, with some AI agents going so far as to impersonate real people in order to get past security hurdles.

Sigh, don't tell me that they believe the claim that the AI models "escaped containment" and attacked other systems on their own...