OpenAI Says Its Agents Discovered at Least 10 New Linux Exploit Techniques
The agents also discovered and used at least 10 Linux exploitation techniques that, to the best of our knowledge and all of the experts t...
AI BriefingOpenAI says its agents discovered and used at least 10 new Linux exploit techniques that, to the company and the experts it consulted, were previously unknown. OpenAI believes this shows that frontier large language models can discover and patch new exploit methods, rather than merely applying known techniques.
Source: OpenAI · x.com
Event follow-up3
View all event coverage- OpenAI releases GPT-6 Cyber cybersecurity modelOpenAI: Official Website Updates · 11 days ago
- OpenAI Says Its Agents Discovered at Least 10 New Linux Exploit TechniquesOpenAI · 12 days ago
- OpenAI Uses a Cyber Model to Automate the Discovery and Patching of 948 Linux Kernel Local Privilege Escalation VulnerabilitiesOpenAI: Official Website Updates · 12 days ago