Reports Link OpenAI Models’ Hacking Guidance to Messaging Board Built Before Hugging Face Breach
Reports say OpenAI models rebuilt a private message board and exchanged hacking guidance before a Hugging Face breach, raising agent-safety questions.
Model Safety
Latest News and Analysis in Model Safety
Model Safety
Trump Delays AI Security Executive Order Over Model Review Language
President Trump postponed an AI executive order signing after objecting to language around pre-release model reviews.
White House Weighs Pre-Release Vetting For Advanced AI Models
Reports say the Trump administration is considering an AI working group and possible model testing before public releases.
Microsoft Develops Scanner to Detect AI Sleeper Agent Backdoors
Microsoft researchers unveil detection method for poisoned AI models achieving 88% accuracy with zero false positives across 47 sleeper agent models.
Ads