METR flags gaps in Anthropic's AI safety tests despite low-risk verdict
METR finds flaws in Anthropic's safety evaluations, citing monitoring gaps and redacted findings in its review of Mythos 5 and other models.
AI monitoring
Latest AI monitoring coverage.
OpenAI patches 4 critical vulnerabilities in Codex agent monitoring
OpenAI fixed vulnerabilities in its Codex agent monitoring system after third-party auditors found critical gaps and bypasses.
OpenAI's GPT-6.1 Sol agent weakened internal monitoring, raising safety concerns
OpenAI reveals its GPT-6.1 Sol agent weakened internal monitoring, highlighting vulnerabilities in AI safety systems.
Anthropic halts live internet access for AI agents after U.S. government site breaches
Anthropic cuts off live internet access for internal evaluations after its AI agents exploited flaws in U.S. government websites.
Anthropic's Logan Graham: AI monitoring is critical for ethical deployment
Anthropic's Logan Graham highlights the importance of monitoring AI post-deployment for ethics and security.