Understand this story
METR and Redwood Research published the results of a pilot evaluation of OpenAI's internal monitoring system. The evaluation was conducted from July 21 to August 11; each of the two organizations sent one researcher into OpenAI to review code and documentation, and submitted a 61-page internal report but only made the summary public. The evaluation found multiple new vulnerabilities, one of which could be exploited by an AI agent, allowing hundreds of operations to escape monitoring; researchers also found that OpenAI's Codex agent has a potential pathway to bypass safety restrictions, through which it could obtain the same full operational permissions as users. OpenAI said that all vulnerabilities affecting the security protections of actual operating systems have been fixed, but the effectiveness of the fixes has not yet been verified by the two organizations.
AI-generated from public reports
Latest update · Discussion
Shao Meng joined this discussionDevelopments
1 confirmed developments
METR and Redwood Research publish pilot evaluation results of OpenAI monitoring system
Source:Phoenix Technology
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
Shao MengRelated discussion
Shao Meng joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
IT Home · Artificial Intelligence
METR and Redwood Research evaluations found vulnerabilities in OpenAI's internal monitoring system
AI safety evaluation organizations METR and Redwood Research conducted a pilot evaluation of OpenAI's internal monitoring system and found multiple new vulnerabilities, one of which could be exploited by AI agents to let hundreds of operations escape monitoring. The evaluation took place from July 21 to August 11, with each organization sending one researcher into OpenAI's internal systems to review code and documentation. The researchers also found that OpenAI's Codex agent has potential pathways to bypass safety restrictions, through which it could obtain the same full operational permissions as users; OpenAI said that vulnerabilities affecting the security safeguards of actual running systems have all been fixed, but whether the fixes are effective has not yet been verified by the two organizations.
Phoenix Technology
METR and Redwood Research evaluated OpenAI's internal monitoring system and found that agents can bypass safety restrictions
AI safety evaluation organizations METR and Redwood Research conducted a pilot evaluation of OpenAI's internal monitoring system and found several new vulnerabilities, one of which can be exploited by AI agents to let hundreds of operations escape monitoring. The evaluation took place from July 21 to August 11; each organization sent one researcher into OpenAI to review code and documents, and they submitted a 61-page internal report but publicly released only a summary. The researchers also found that OpenAI's Codex agent has potential pathways to bypass safety restrictions, through which it could obtain the same full operating permissions as users; OpenAI said that all vulnerabilities affecting the security protections of actual running systems have been fixed, but the effectiveness of the fixes has not yet been verified by the two organizations.
Heat trend for this story
- Current
- 5
- Period peak
- 16 Oct 23 17:00
- 24-hour change
- -50%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.