Safety overview: GPT-6 Astra

What changed

GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Path to Astra: critical capabilities and frontier safeguards
• OpenAI’s Astra model is on the way — and very good at breaking into computer systems
• OpenAI launches Astra, its powerful (and controversial) new model

• Path to Astra: critical capabilities and frontier safeguards similarity 0.54
• OpenAI’s Astra model is on the way — and very good at breaking into computer systems similarity 0.30
• OpenAI launches Astra, its powerful (and controversial) new model similarity 0.29