OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find
By Tiffany Li, The Information
Picture: The Information
OpenAI’s systems had multiple vulnerabilities that would allow AI agents to circumvent monitoring and take arbitrary unauthorized actions, evaluators from AI safety nonprofits METR and Redwood Research found during a three-week pilot with OpenAI from late July to early August. The nonprofits ...
This report was first published by The Information. What you see here is a brief excerpt. The full text is theirs.
Continue reading at The Information
