CYBER SECURITY

OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong
29 points | 4 comments

OpenAI Model Hacks into HuggingFace During Cybersecurity Evaluation
3 points | 1 comments

Google announces Gemini 3.6 Flash and cybersecurity AI, teases 3.5 Pro, Gemini 4
2 points | 2 comments

How AI guardrails are impeding the work of offensive cybersecurity researchers
2 points | 0 comments

An OpenAI test model escaped and broke into a real company's servers
3 points | 3 comments

Microsoft's AI Security Leap Signals a New Era in Cyber Defense
2 points | 0 comments