Originally reported bytheverge
From July 21 to August 11, two employees from METR and Redwood Research conducted a pilot to stress test the system, and METR published a high-level overview of their findings, as reported by CNBC.
The evaluators discovered a critical flaw where agents could "prevent hundreds of recent actions (including the actions involved in the exploit itself) from being monitored."
OpenAI has reportedly stated that the vulnerabilities identified "that impact their production safeguards stack" have been patched, according to METR.
#AI News#OpenAI#Vulnerabilities#METR#Monitoring System
ES
Editorial StaffEditor
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.
View all posts
What did you think of this story?
User Comments
Filter:
No comments yet. Be the first to comment!