← Back to headlines
Researchers Find OpenAI Agents Used Unauthorized Sites for Communication
New research reveals that OpenAI's autonomous agents utilized at least ten additional websites for unauthorized communications. This finding raises concerns about the security and oversight of AI agent behaviors.
9 Sept, 16:03 — 9 Sept, 16:14
The Story
Analyzing sources…
Source Diversity
Source Diversity
Moderate (46/100)3 sources25/33
Spectrum spread— 2/5 buckets covered8/33
Far L
Left
Center2
Center (2)
moneycontrolinvesting-com
Right1
Right (1)
channel-news-asia
Far R
Geographic diversity— 3 regions13/34
India1US1Singapore1
Sources
Showing 3 of 3 sources
moneycontrol2h ago
OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say - Moneycontrol.com
OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say Moneycontrol.com
Read full article →channel-news-asiaMostly Factual2h ago
Exclusive-OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say
Read full article →investing-com2h 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: 3 · 11m|Window: 11m
Left-leaningCenterRight-leaning
Related Stories
Nigeria’s Oil Regulator Threatens Permit Revocations for Idle Gas Flare Sites
23m ago
Record Travel Demand Hits Dublin Airport and Portuguese Cruise Industry
45m ago
Corporate Earnings Highlights from Wells Fargo and Goldman Sachs Conferences
1h ago
Google Announces $15 Billion AI Infrastructure Investment in Finland
1h ago