← Back to homepage
OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
Sources
2
Coverage
Limited spectrum
Sentiment
-0.50
◀ Left 50%Centre 50%Right 0% ▶
How we rate bias →This story is currently only covered by 2 sources from a limited 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)
Guardian Business
OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk
Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Institute.
AISI described the actions carried out by the agents, the term for AI systems that can perform tasks without human he…
5 Aug, 08:40
Centre
(1)
FT UK
OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says
AI Security Institute warns tools undertook ‘potentially harmful activity directed at real people and organisations’
4 Aug, 21:46
Right
(0)
No coverage from this perspective yet