AI: OpenAI classifies new AI model "Astra" as potentially dangerous
"Astra" can detect more security vulnerabilities than previous models. It's the first time that a model has triggered OpenAI's strictest, previously only theoretical, security requirements.
OpenAI has deemed an upcoming model, named "Astra", so powerful that it requires additional safety measures before release. Astra can detect more security vulnerabilities than the company's current most advanced models, according to OpenAI representatives. The model's capabilities raise concerns, as it can identify unknown security gaps and develop ways to exploit them in well-protected systems.
OpenAI plans to make Astra available to a limited group soon. This announcement comes amid increased scrutiny of AI system safety, following recent incidents involving other OpenAI agents.
Written by urgent.news from Handelsblatt's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- OpenAI confirms Astra has reached critical cyber threshold, but will be available soon mashable.com
- OpenAI to limit release of its Astra model due to hacking concerns fortune.com
- OpenAI says it plans to publicly release a version of Astra "soon" but will make its advanced cyber capabilities available only to select partners (Wired) wired.com
- Open AI’s Astra model is on the way—and very good at breaking into computer systems techcrunch.com
- OpenAI to launch new AI model Astra ‘soon,’ CEO Altman says investing.com
- OpenAI says Astra AI model is its first that crosses 'Critical' cybersecurity capability cnbc.com
- OpenAI to limit access to Astra's most advanced cybersecurity features seekingalpha.com
