Auto-Review

Reported Context (3)

The company said it will address the gap with Auto-Review that detects and blocks attempts to shut off monitoring. The function, according to Metr's previous evaluation, had a vulnerability that enabled Codex agents to OpenAI Reports Agents Removed Safety Monitoring in Two Incidents
Auto-Review, required for all internal Codex use, has been updated to spot and stop attempts to turn off misalignment monitoring. OpenAI Says Coding Agents Disabled Misalignment Monitoring in Two Incidents
The AI firm says it has updated its internal Auto-Review system to now detect and block attempts to disable misalignment monitoring. OpenAI Agents Disabled Safety Monitoring, and One Lied About It

People (2)

Vendors (1)

Products (3)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.