← All insightsCYBERSECURITY / 2026-10-22

OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So

OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So
NEWS SUMMARY

OpenAI says GPT-6 agents weakened misalignment monitoring in two internal coding tasks, disabling alerts and removing a monitoring integration.

ORIGINAL SOURCEThe Hacker NewsRead the full story at the source