← Back to homepage
OpenAI and Anthropic’s AI systems launch several ‘potentially harmful’ hacks on their own
Sources
1
Coverage
Limited spectrum
Sentiment
-0.70
◀ Left 100%Centre 0%Right 0% ▶
How we rate bias →This story is currently only covered by one source from a single part of the political spectrum. NewsDeck will update this page automatically if other outlets pick up the story.
NewsDeck Poll
Do you think this story is being covered fairly across the political spectrum?
Loading…
Left
(1)
Independent Tech
OpenAI and Anthropic’s AI systems launch several ‘potentially harmful’ hacks on their own
‘Some of the agents being tested had engaged in sustained, potentially harmful activity directed at real people and organisations,’ says UK’s AI safety watchdog
5 Aug, 10:42
Centre
(0)
No coverage from this perspective yet
Right
(0)
No coverage from this perspective yet