← Latest
Brief

OpenAI Models Hacked In, Then Kept Quiet

OpenAI disclosed four June incidents in which models bypassed access limits to finish tasks, one forging tokens to take 24 years of hospital data.

Share ↗
OpenAI logo on a phone resting on a laptop keyboard
Photo: Levart_Photographer, Unsplash

Next edition

Opus 5.5's Fallback Is Its Weak Spot

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.