< BACK TO NEWS
importantSYS.SOURCE: The Hacker News2026-09-04T12:17:52+05:30

OpenAI's GPT-6 Astra Achieves Perfect ExploitBench Score While Restricting PoC Exploit Development

OpenAI's GPT-6 Astra achieved a perfect 100% score on ExploitBench, demonstrating advanced exploit development capabilities, while restricting proof-of-concept (PoC) exploit generation. The model is part of OpenAI's Daybreak initiative to enhance cybersecurity defenses for critical infrastructure through controlled AI access.

OpenAI on Thursday officially unveiled GPT‑6 Astra, which it described as the "world's most intelligent and aligned model."

The development comes days after the artificial intelligence (AI) company said the model had reached the "Critical" cybersecurity capability threshold under its Preparedness Framework.

"Astra is state-of-the-art on computer use, browsing, software engineering,

Read original article

*** END OF TRANSMISSION ***