OpenAI scans the Linux kernel and finds 948 privilege escalation vulnerabilities; out of 2,308 candidate issues, 1,724 were successfully reproduced.
OpenAI releases a security report using undisclosed cybersecurity models to scan the Linux kernel. The process identified 2,308 issues, successfully reproduced 1,724 of them, generated 948 privilege escalation exploits, and incurred a total API cost of $1.2134 million.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome