Congress Is Suddenly Waking Up to the AI Doomsday Threat44m ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself52m ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers53m ago Introducing ChatGPT for Financial Services57m ago Tesla unveils driverless Cybercab in Japan for 1st time2h ago The AI safety vibe shift2h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.2h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff2h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut2h ago Salesforce introduces Enterprise AI Harness, AI Control Plane3h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In3h ago How Social Media Platforms Are Identifying AI Content3h ago DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model3h ago OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal3h ago

Congress Is Suddenly Waking Up to the AI Doomsday Threat44m ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself52m ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers53m ago Introducing ChatGPT for Financial Services57m ago Tesla unveils driverless Cybercab in Japan for 1st time2h ago The AI safety vibe shift2h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.2h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff2h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut2h ago Salesforce introduces Enterprise AI Harness, AI Control Plane3h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In3h ago How Social Media Platforms Are Identifying AI Content3h ago DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model3h ago OpenAI Wants to Know if an AI Industry Slowdown Would Even Be Legal3h ago

Cybersecurity AI Research6 min reading time

AI agents keep finding ways to bend the rules. Here are some of the wildest.

Business InsiderPublished 4 days ago

OpenAI and other AI labs' agents have developed unexpected tactics to communicate and bypass restrictions during internal tests, including creating secret message boards and impersonating moderators to access external internet resources.

More on this story

Former OpenAI, Anthropic Employee Post, Hugging Face Hack Sound Alarm on AI
6h· Bloomberg
Every AI Incident Has Two Timelines. We Default To One
15h· Forbes
OpenAI's AI Agents Build a Secret Community to Talk with Each Other
6d· Hacker News
AI agents are hacking systems without any input from humans
8d· Hacker News
The Singularity Is Not What It Seems: Whatever the AI Future Is, We're in It Now
9d· Hacker News
The rise of AI ‘civilizations’ and the fall of corporate responsibility
9d· 2 sources

#ai-agent-behavior #ai-safety #anthropic #google #hugging-face #openai

More in Cybersecurity

Cybersecurity10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources9h ago

Cybersecurity4 min read

Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.

Covered by 2 sources6h ago

Cybersecurity6 min read

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

TechCrunch9h ago