The AI Superintelligence Slowdown
See all Stories
J
OpenAI’s misalignment monitoring system had “a number of novel vulnerabilities,” third-party evaluators found.
From July 21st to August 11th, 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. One exploit would have allowed agents to “prevent hundreds of recent actions (including the actions involved in the exploit itself) from being monitored.”
OpenAI “has stated” that the vulnerabilities identified “that impact their production safeguards stack” have been patched, METR says.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
Most Popular
Most Popular
- Sam Altman addresses RAM comments: People should ‘put as much as they want in their computers’
- Anker’s new window-mounted camera monitors the outside of your home from within it
- Those Jeff Bezos hair transplant photos are very fake
- The Legend of Zelda: Ocarina of Time never gets old
- Bambu’s nine-nozzle H3C foretells the future of 3D printing
