AI RADARМоделі
159•09/14/2026, 05:18•2 min read
GPT-6 Astra Vulnerability Found via Keyboard Layout Mismatch
#GPT-6#AI Safety#Jailbreak#LLM
The GPT-6 Astra model bypasses safety filters when prompts are typed in the wrong keyboard layout, such as Ukrainian text using English characters.
AI Radar • Plus Tier
Full Engineering Breakdown Available in Plus Plan
Daily technical analyses, benchmark reviews, model changes, and vibe coding case studies unlock in the Plus plan.
Discuss in community
Share your questions and insights with developers