On Tuesday, staffers from OpenAI, Anthropic, Google, and other tech companies met with White House officials to review the administration's new framework for evaluating advanced AI models' cyber capab…
OpenAI has built GPT-Red, an automated red-teaming model that hunts for security flaws in its own AI systems, and will not release it due to safety concerns. In tests, GPT-Red cracked 84% of attack sc…
OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest ver…
FLARE-AI, a crowdsourced platform for reporting AI model flaws, launched to promote transparency and accountability in artificial intelligence. CSET's Jessica Ji endorsed the initiative as a positive …
A group of AI researchers launched FLARE-AI, a crowdsourced website for reporting and tracking AI harms, enabling users to flag issues like malware generation or privacy leaks. The open-source system …