AICNBC Techabout 1 hour ago
OpenAI Monitoring System Has Vulnerabilities
2 min read
Nonprofit evaluators METR and Redwood Research found vulnerabilities in OpenAI's internal monitoring system during a three-week pilot from July 21 to Aug. 11th. The team discovered an exploit preventing hundreds of actions from being monitored, though OpenAI stated it has since patched the issues affecting production safeguards.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
