Continue reading “Gemini hacked multiple companies in cybersecurity test gone awry”
Tag: Cybersecurity
Inside the suddenly explosive world of AI safety
AI agents can now remember and hackers can ‘poison’ their memories—a new
Gemini 3.8 Flash is out with a new focus on cybersecurity
Someone targeted security researchers using a fake crypto conference as a lure
Researchers complain that OpenAI revoked their access to limited cyber program
Prototype Development Laboratory (PDL) Capabilities
Chinese AI Model Kimi Escaped Its Cybersecurity Testing Environment
Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
NVIDIA launches 'Open Secure AI Alliance' initiative to improve cyber defense
Check Point warns of SmartConsole zero-day exploited in attacks
New InfraTrust report reveals infrastructure flaws admins should patch first
AI is rewriting cybersecurity's rules
Felons, Fraudsters Flog Offensive Cybersecurity Startup
OpenAI restricts GPT-5.6 Sol to approved users during White House cyber review
Anthropic gets US government's permission to redeploy its Mythos cybersecurity AI model
CISA Tells US Agencies to Fix Security Bugs in as Little
Anthropic just released public Mythos-class AI model called Claude Fable
