Safety overview: GPT-6 Astra

by script • 2026-09-03 23:09 • Comments Off

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.

This article has been indexed from OpenAI News

Read the original article:

Safety overview: GPT-6 Astra

← BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA

TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning →

Read the original article:

Post navigation