gl
o
signal
← All stories
Signal
1 source
·
1h ago
OpenAI details GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery so it can fix bugs before wider deployment
Training strong automated safety red-teamers to improve robustness. — Summary — Problem
Related Stories
Identity Attacks Overtake Exploits as Top Ransomware Cause
AI slop movies are the new direct-to-video cash grabs
OpenAI details GPT-Red, an internal automated red-teaming model that helps it find and fix prompt injection vulnerabilities at scale before wider deployment
Dave Brown, AWS SVP of Compute, AI, and Platform, is leaving the company after 19 years for a new job; he is a member of the S-team that advises CEO Andy Jassy
ZTE's AI new calling builds an open and intelligent telecom ecosystem, transforming from basic voice call to an AI-powered service hub