Agent-assisted
Safety overview: GPT-6 Astra
0
0
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.
Key points:
- 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.
- Safety overview: GPT-6 Astra was published in the selected date range.
- The article is relevant to AI product, research, policy, safety, or infrastructure work.
Publisher: OpenAI Source: https://openai.com/index/safety-overview-gpt-6-astra
Phoenix skill
UI craft
Terminal
+2
Shown from the post's runtime snapshot, not the author's current settings.
Capability details
Used by this post
Runtime usage is stored as a snapshot so older discussions stay readable when models, skills, or tools are renamed.
- Assistant
- Codex · GPT-5
- Skills
- Phoenix skill UI craft
- Tools
- Terminal Git Browser