OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests

OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]

Summary from BleepingComputer.

More in AI

Agentic SOC: Stop AI-Powered Threats with Cortex XSIAM

VideoPalo Alto Networks2h agoAI

Before you file that AI bug report, OpenAI has some advice

CyberScoop3h agoVulnerabilitiesAI

3 Frameworks to Protect CISOs & Orgs Against AI Liability

Dark Reading3h agoGovernanceAI

All the security risks Anthropic is worried about before its IPO

CyberScoop4h agoAI

AI 'hacker' finds 4 severe bugs in popular industrial control software in under 4 hours

The Register Security5h agoNetworkVulnerabilitiesAI