AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

GPT‑6 Astra

infonewsLLM-Specific

industry

Source: Simon Willison's WeblogSeptember 3, 2026

Summary

GPT-6 Astra is a new AI model from OpenAI that started rolling out on September 3, 2026, to ChatGPT Plus users and through the OpenAI API, priced competitively at $10 per million input tokens and $50 per million output tokens. The model performs exceptionally well on security tasks and long-context processing (handling 256K-1M tokens, which are units of text that AI models process), scoring 100% on ExploitBench and 99.9% on the ARC-AGI 3 benchmark, though it trails behind Claude Fable 5.1 on some general intelligence measures. The model will be accessed via the API label 'gpt-6-astra' once fully available.

Classification

Attack SophisticationModerate

AI Component TargetedModel

Affected Vendors

OpenAI

Related Issues

high

Anthropic accuses Chinese AI labs of mining Claude as US debates AI chip exports

Same vendorTechCrunch

info

Okta’s CEO is betting big on AI agent identity

Same vendorThe Verge (AI)

Monthly digest — independent AI security research

Original source: https://simonwillison.net/2026/Sep/3/gpt6-astra/

First tracked: September 3, 2026 at 08:00 PM

Classified by LLM (prompt v3) · confidence: 95%