OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

AI Summary

Evaluators from METR and Redwood Research found that OpenAI systems had vulnerabilities that could let AI agents bypass monitoring and take unauthorized actions. The findings came from a three-week pilot with OpenAI conducted from late July to early August.

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 ...