Storia in 12 fonti

OpenAI clears Astra for release after critical cybersecurity rating

The company said Astra is the first model it has designated "Critical" under its Preparedness Framework, capable of finding and exploiting unknown security flaws without human guidance

Raccontata da

economictimes.indiatimes.com

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

qz.comStai leggendo7 g fa

OpenAI clears Astra for release after critical cybersecurity rating

The company said Astra is the first model it has designated "Critical" under its Preparedness Framework, capable of finding and exploiting unknown security flaws without human guidance

originale

Timeline cronologica

martedì 1 settembre 2026·fortune.com
OpenAI to limit access to Astra model's advanced cyber features due to hacking concerns | Fortune
OpenAI says Astra is considerably more capable at cyber tasks than GPT-5.6 Sol. Following the Hugging Face incident, it is being especially cautious about releasing it.
martedì 1 settembre 2026·wired.com
OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilities
The company will give select partners early access to its Astra AI model—so they have time to shore up their defenses.

OpenAI clears Astra for release after critical cybersecurity rating

Confronto fonti

OpenAI clears Astra for release after critical cybersecurity rating

Timeline cronologica

OpenAI to limit access to Astra model's advanced cyber features due to hacking concerns | Fortune

OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilities

Astra Hits Critical and OpenAI Releases It Anyway

OpenAI flags Astra AI model as having critical cyber abilities

OpenAI’s Astra Crosses ‘Critical’ Cyber Threshold After Finding Zero-Days

OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilities

OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities - Decrypt

OpenAI flags Astra AI model as having critical cyber abilities

OpenAI's Astra model is on the way — and very good at breaking into computer systems | TechCrunch

OpenAI Astra: OpenAI says upcoming model is so capable it requires stronger guardrails - The Economic Times

OpenAI's Astra Crosses the "Critical" Cybersecurity Threshold: AI Agents Need Stronger Execution Boundaries

OpenAI says its next model finds security flaws nobody has found yet

OpenAI’s Astra Crosses ‘Critical’ Cyber Threshold After Finding Zero-Days

OpenAI clears Astra for release after critical cybersecurity rating

OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder

OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities - Decrypt

OpenAI confirms Astra has reached 'critical' cyber threat level

OpenAI launches GPT-6 Astra amid fears of cybersecurity risks

OpenAI Astra Rolls Out With Alignment Controls and Restricted Cybersecurity Access

OpenAI Astra: What Published Cybersecurity Testing Means for AI Automation

OpenAI Launches Astra With Staged Access to Its Most Advanced Cyber Capabilities

OpenAI Astra model: OpenAI launches new Astra model amid growing scrutiny over agents' safety - The Economic Times

Astra Hits Critical and OpenAI Releases It Anyway