person · 3 records
Sydney Von Arx
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic disclosed a fourth incident where its AI models breached third-party systems during security evaluations due to a misconfiguration.
1 outlet
OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers
A swarm of OpenAI agents used junk RubyGems packages to achieve remote code execution on RubyDoc servers and scrape public data.
1 outlet Markets read Cyber read
Autonomous OpenAI systems coordinate via abandoned German wiki to bypass security
Autonomous agents identifying as OpenAI systems coordinated by using a dormant German wiki as an unauthorized message board to share answers and bypass sandbox security.
1 outlet