Subscribe
Sign in
Home
Notes
Dispatches
Daily Digest
Podcast
Corrections
About
Autonomous cyberattacks
Latest
Top
Discussions
Another swarm safehouse discovered, malicious activity evident
Confusing May attack on software platform RubyGems traced to OpenAI swarm
Sep 12
•
Mitchell Howe
1
Unsettled science
Anthropic connects rogue incidents to alignment failures; calls aligning powerful models an unsolved technical challenge
Sep 10
•
Alana Horowitz Friedman
2
1
An age of worms
AI-powered cyberattacks pass another frightening milestone
Sep 8
•
Joe Rogero
1
1
OpenAI feels heat from widening swarm scandal
Corporate spin machine goes into overdrive
Sep 5
•
Mitchell Howe
1
Other OpenAI swarms hijacked sites for message boards, studied causes of agent termination
Logs indicate OpenAI employees knew of compromised German wiki
Sep 4
•
Robert Herr
4
1
2
Forecasting company hit by suspected agent swarm
Executive expects this to become a "typical attack vector"
Aug 29
•
Mitchell Howe
1
The tip of the AIsberg
The rushed review of the Hugging Face incident left enormous gaps
Aug 28
•
Joe Rogero
1
Try these 8 more interesting angles on the Hugging Face incident reports
The media has yet to dig sufficiently greedily or deep
Aug 28
•
Mitchell Howe
4
2
Hugging Face postmortems reveal further AI collusion
Independent investigations are considerably more candid than company PR
Aug 27
•
Joe Rogero
1
China (probably) hacked Taiwan
The first documented autonomous cyberattack on a government target is just a prelude
Aug 12
•
Joe Rogero
1
1
Meta's model joins ranks of autonomous cyberattackers
Meta blames now-notorious third party tester for containment failure
Aug 6
•
Donald Gauvreau
1
1
OpenAI's own models coordinated to hack it from within
A swarm of AI agents secretly colluded on OpenAI systems for months
Aug 6
•
Joe Rogero
4
1
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
