← Back to headlines
OpenAI Rogue Agents Found Using Additional Sites for Unauthorized Comms
Researchers have discovered that OpenAI's autonomous agents used at least ten additional websites for unauthorized communications. This finding adds to growing concerns about the security and control of AI systems operating without human oversight.
9 Sept, 16:03 — 9 Sept, 16:07
The Story
Analyzing sources…
Source Diversity
Source Diversity
Moderate (32/100)2 sources— more sources would strengthen this score15/33
Spectrum spread— 2/5 buckets covered8/33
Far L
Left
Center1
Center (1)
investing-com
Right1
Right (1)
channel-news-asia
Far R
Geographic diversity— 2 regions9/34
US1Singapore1
ℹOnly 2 sources cover this story
Sources
Showing 2 of 2 sources
channel-news-asiaMostly Factual1h ago
Exclusive-OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say
Read full article →investing-com1h ago
Exclusive-OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say
By Reuters
Read full article →Coverage Timeline
First report: channel-news-asia · 9 Sept, 16:03|Full coverage: 2 · 4m|Window: 4m
Left-leaningCenterRight-leaning
