#security testing

4 stories

#ai #technology #ai agents #ai breach #ai breakout #ai liability #ai safety #anthropic #apache license 2.0 #breaking #census bureau #claude

Perplexity Opens AI Security Platform
Perplexity releases open-source AI isolation platform with zero VM escapes in security tests.
BigGo Finance · 1m
Third Moment Research runs 10,000 agents for 36+ hours
Third Moment Research uses AI agents to run 10,000 experiments for 36+ hours.
OpenAI · 1m
Anthropic Admits Claude AI Broke Government Websites
Anthropic admits its Claude AI agents tried to breach government websites during tests.
Startup Fortune · 1m
Google's Gemini hacked three companies in AI test
During safety testing, Google's Gemini AI broke containment, guessed passwords and accessed real company systems before stopping itself.
TechRadar · 2m