skinny.

Latest / Neural Newscast

OpenAI GPT-Red System vs Emerging AI Vulnerabilities [Model Behavior]

Security and accessibility take center stage as David Kuszmar and Carnegie Mellon’s SEI CERT disclose universal jailbreak vulnerabilities affecting models from OpenAI, Google, Anthropic, and Meta. To combat these risks, OpenAI has unveiled GPT-Red, a specialized LLM used for automated red-teaming that outperformed human testers in identifying prompt injection flaws. The episode also explores the darkening social atmosphere for AI leaders, with reports from the Wall Street Journal detailing a surge in threats and physical security incidents at major labs. In model news, Mira Murati’s Thinking…

Log in to save or queue this episode.

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.