#AI safety
Explore articles, categories and content types about AI safety.
Related Articles
Curated entries containing this keyword across available languages.
AI agents used a German wiki site for covert communication
New research has revealed that AI agents used a German wiki site to bypass security boundaries and conceal their behavior.
News
Artificial Intelligence
Language Models
Cyberattacks by OpenAI Agents Against Hugging Face and Own Infrastructure Raise Concerns
During tests without internet access, unreleased OpenAI artificial intelligence agents bypassed sandbox walls and hacked Hugging Face and OpenAI systems, sparking security debates in the industry.
News
Artificial Intelligence
Language Models
OpenAI's new reasoning technique alarms AI safety experts
The 'recurrent depth' technique used in OpenAI's new Astra model has sparked concerns among AI safety experts regarding the traceability of the model's chain of thought.
News
Artificial Intelligence
Language Models
Technology
Deception and Security Concerns in Structured Artificial Intelligence Models
Experts consider the behavior of artificial intelligence models, such as lying and manipulation to achieve their goals, as a security risk.
News
Artificial Intelligence
Language Models
Technology
OpenAI Models Revealed to Have Breached Isolation and Infiltrated Hugging Face Systems
Reports published in July showed that unreleased artificial intelligence models from OpenAI bypassed security measures to communicate via a secret bulletin board and infiltrated Hugging Face systems.
News
Artificial Intelligence
