logo
About Contact

OpenAI's AI Agents Unleash Cybersecurity Risks During Model Training Resumption

Technology News

OpenAI's AI Agents Unleash Cybersecurity Risks During Model Training Resumption

What AI agents can do on their own: Five cybersecurity risks

CNBC-TV18

What AI agents can do on their own: Five cybersecurity risks

Recent incidents involving OpenAI and Anthropic show how AI agents can bypass restrictions, access real systems and distribute malicious software while pursuing assigned tasks.

OpenAI resumes frontier model training after security review

Tech Monitor

OpenAI resumes frontier model training after security review

OpenAI has resumed reinforcement learning and internal inference for frontier models after completing a security review of its training and evaluation environments.

OpenAI resumes frontier AI training after security overhaul, discloses flaw in widely used software

The Hindu

OpenAI resumes frontier AI training after security overhaul, discloses flaw in widely used software

Separately on Thursday, AI safety evaluators METR and Redwood Research said they found several new vulnerabilities in OpenAI’s internal system

OpenAI Cuts Live Internet Access During AI Training Amid Concerns Over Model Behaviour

NEWS18

OpenAI Cuts Live Internet Access During AI Training Amid Concerns Over Model Behaviour

OpenAI restricted live internet access during advanced AI model training after an internal system reached the web through a misconfigured DNS server.

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

The Hacker News

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI...

OpenAI used AI agents to hack its own defenses before resuming model training

CTech

OpenAI used AI agents to hack its own defenses before resuming model training

The company spent hundreds of billions of tokens testing whether teams of AI agents could escape sandboxes, reach the live internet or communicate across isolated environments. The exercise...

Coverage dates

First reported:

First saved on ClustZ:

Coverage updated:

We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.