OpenAI's Astra is first model to hit 'Critical' cyber threshold
OpenAI says Astra is its first model to reach the 'Critical' cybersecurity capability threshold under its Preparedness Framework, scoring 100% on ExploitBench and finding two V8 zero-days during testing. Access to its cyber capabilities will be limited when it ships 'soon.'
How this story unfolded
4 weeks · 15 reports · 16 community posts · 31 of 36 shown
- Aug 7
Responding to the next frontier of critical cyber capabilitiesopenai.com
OpenAI Pauses Some Work on New Astra Model Over Cyber Concernsbloomberg.com
OpenAI puts the brakes on a new model because it’s supposedly too powerfultheverge.com
The AI model OpenAI won’t release yet — and what it found in testingthenewstack.io
OpenAI says it slowed Astra model development over security concernstechcrunch.com
- Aug 10
OpenAI's Next AI Model Astra Shows Cyber Performance Strong Enough to Trigger Pausethehackernews.com
OpenAI tightens controls on its new model over cybersecurity risks, as AI security debate intensifiescnbc.com
OpenAI’s Upcoming Astra Model Raises Autonomous Cyberattack Concernssecurityweek.com
OpenAI Says Its Next AI Model Astra May Be Too Dangerous, Pauses Developmentdecrypt.co
OpenAI locks down Astra after model raises first-ever critical cyber capability fears
- Aug 30
- Aug 31
- Sep 1
OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilitieswired.com
- Sep 2
OpenAI by email
Get an email when OpenAI has news
No news that day, no email.
More stories today
- Lyte closes $165M round at $1.6B valuation
- Meta settlement could clear way for new AI product launches
- Z.ai opens first Tmall store for AI subscriptions
- Fable 5.1 Max users share setup tips and warnings
- Opinion: Next DSM should assess algorithms' role in eating disorders