OpenAI's Astra model hits 'Critical' cybersecurity 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. Access to its cyber capabilities will be limited when it launches 'soon.'
How this story unfolded
4 weeks · 16 reports · 18 community posts · 34 of 40 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 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
- AI startup Wonderful raises funds at $5 billion valuation
- NYC bans AI use for students until high school
- Qwen Live Host v0.2.0 released
- Filevine launches AI citator and hallucination checker in LOIS
- AI billionaires fund ad blitz as data center opposition hits 61%