OpenAI investigating 'dozens' of instances of agents acting improperly
BBC • 9/4/2026 – 9/26/2026
Summary
No summary yet.
Advertisement
Cluster Activity
1
4
1
2
4
3
2026-09-042026-09-26
Lindy Score Breakdown (V4.2)
17h
Age
10
Sources
from cluster
22
Hours Since Seen
Final Score40/100
CategoryBreaking
StatusActive
Recency Multiplier73% (0.5^22/48)
Hero EligibleYes
Story Timeline
- 2026-09-04
- 2026-09-05
- 2026-09-08
- 2026-09-12
- 2026-09-25OpenAI investigating 'dozens' of instances of agents acting improperly (current)
- 2026-09-26
Score BreakdownRisk 30
Source Reputation: Moderate trust (8/20 pts)
Consensus: Strong consensus: 10 independent sources
Age: Breaking news - too recent to assess longevity
Stories gain Lindy status through source reputation, network consensus, and time survival.
Same Story from 11 sources
OpenAI tools post user images from ChatGPT online
Deutsche Welle • Today
OpenAI says its AI agents posted user images online in error
South China Morning Post • Today
Rogue OpenAI agents accessed US government websites
Politico • Today
Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
TechCrunch • 1 day ago
For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
TechCrunch • 1 day ago
One company is at the center of a wave of rogue AI attacks
The Verge • 1 day ago
OpenAI’s rogue AI tried to hack another company in May
The Verge • 2 weeks ago
OpenAI agents hacked a software service before the Hugging Face incident
Engadget • 2 weeks ago
Rogue OpenAI agents hijacked a German wiki, and it stayed secret for weeks
Euronews • 2 weeks ago
OpenAI responds after report exposed another incident in which its AI agents went rogue
Engadget • 3 weeks ago
Breaking Similar stories
OpenAI says its AI agents posted user images online in error
South China Morning Post • Today
OpenAI Agents Hacked Into an Australian Government Website. Who’s Responsible?
The New York Times • 1 day ago
OpenAI CEO: Tech companies don’t ‘have all the answers’ on AI policy
Al Jazeera • 2 days ago
Inside the FBI hack: Agents fearful and angry after 'dangerous' data breach
BBC • Today
Special agents' blood and urine test results stolen in FBI hack
BBC • 1 day ago
OpenAI tools post user images from ChatGPT online
Deutsche Welle • Today
OpenAI agent 'infiltrated' Australian government website, PM says
BBC • 2 days ago
SoftBank takes on junk-bond debt at record yields to fund OpenAI ambitions
Japan Times • 2 days ago
Australia Investigates OpenAI Hack on Public Health Care Site
The New York Times • 2 days ago
Venezuela’s acting leader, at UN for first address, promises elections at the ‘right moment’
AP News • 2 days ago
Anti-Lindy Similar stories
Rogue OpenAI agents hijacked a German wiki, and it stayed secret for weeks
Euronews • 2 weeks ago
OpenAI agents hijacked German website in previously undisclosed AI breakout this spring
Japan Times • 3 weeks ago
FBI says investigating breach of ‘very sensitive’ data by hackers
Al Jazeera • 3 days ago
Australia says OpenAI agent breached government health data portal
Reuters • 3 days ago
OpenAI AI agent breached Australian government website, PM says
France24 • 3 days ago
Two children among dead in Israeli strikes on Lebanon
France24 • 2 weeks ago
Hurricane Polo expected to reach Category 5 as it nears Mexico’s Pacific coast
Mexico News Daily • 5 days ago
Pakistan shoots down eight drones ‘launched from Afghanistan’ amid fresh border clashes
The Hindu • 3 days ago
Pakistan says time has come to implement Mecca defence pact
Middle East Eye • 1 week ago
Xi’s US visit begins with rare airport welcome from Trump, trade truce extension
South China Morning Post • 3 days ago