← Latest
Brief

GPT-6 Cyber's Exam Recreates OpenAI's Own Breach

OpenAI rates GPT-6 Cyber Critical and tests its restraint with a honeypot modeled on its own models' July break-in at Hugging Face.

Share ↗
GPT-6 Cyber title over a glowing horizon and floating code symbols
Image: OpenAI

Next edition

Traders Wiped $700 Billion Off OpenAI, Anthropic

AI Secret

AI Secret Membership

Choose your edge.

Independent AI analysis. Your own agent to take it further.

AI Secret

AI Secret Membership · Step 1 of 2

Your next chapter starts here.

Enter your email to choose your membership. Use the same email if you already read AI Secret.

Already a member? Sign in

AI Secret

Your free daily briefing

Check your inbox.

We've sent a confirmation link to . Follow the link to verify your email and complete your free subscription.

Free membership includes the daily briefing. Paid Deep Dives require a paid membership.