VulnBench: Can LLMs find the same security bugs twice?

A website called VulnBench is exploring whether large language models can identify the same security bugs multiple times. The site is linked to a discussion on Hacker News, where users can comment on the topic. The discussion has not yet received any comments. VulnBench is investigating the capabilities of large language models in finding security vulnerabilities. The website and discussion thread are available for further information.