27
Aug
Here’s all the times AI has gone rogue and hacked other companies
-
By
dealharbour
In July, OpenAI admitted that one of its agents tasked with completing a cybersecurity experiment broke out of containment and hacked A...
Tag Archives: Rogue
27
Aug
OpenAI’s rogue AI model incident was worse than we thought
-
By
dealharbour
In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI ag...
23
Aug
Frontier AI labs still won’t say how they’d contain a rogue model
-
By
dealharbour
Few of the top AI labs have published or demonstrated containment response plans, according to a recent study. A containment plan spell...
16
Aug
Rogue AI aren’t science fiction anymore
-
By
dealharbour
This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI safety, follow Robert H...